Upload 11 files

A2 #Q6 BLEU Scores CSV file.csv

@@ -0,0 +1,1001 @@
+Sample,BLEUSeq2seq Score,BLEU LTSM Score
+1,0.399632095,0.028610696
+2,0.860571445,0.326800669
+3,0.685595153,0.741736946
+4,0.578926787,0.777621286
+5,0.224814912,0.9
+6,0.224795616,0.426231956
+7,0.14646689,0.9
+8,0.792940917,0.711575621
+9,0.580892009,0.294392584
+10,0.666458062,0.304737051
+11,0.116467595,0
+12,0.875927882,0.9
+13,0.765954113,0.9
+14,0.269871289,0.06120956
+15,0.245459974,0.681207817
+16,0.246723608,0.9
+17,0.343393794,0
+18,0.519805145,0.422093015
+19,0.445556015,0.9
+20,0.332983312,0
+21,0.589482316,0.731325697
+22,0.211595089,0
+23,0.333715719,0.9
+24,0.393089475,0.867936226
+25,0.464855987,0.451630237
+26,0.728140769,0.770556212
+27,0.259739026,0.605986227
+28,0.511387551,0.57307641
+29,0.573931655,0.405422678
+30,0.13716033,0.9
+31,0.586035882,0
+32,0.236419299,0.592435865
+33,0.152041274,0.391211195
+34,0.85910843,0.36972991
+35,0.872505626,0.20567295
+36,0.746717878,0.565274061
+37,0.343691015,0.165002416
+38,0.178137691,0.701349388
+39,0.647386421,0
+40,0.452121995,0
+41,0.197630588,0.640732985
+42,0.496141528,0.9
+43,0.127510817,0
+44,0.827456322,0.348280425
+45,0.307023985,0.9
+46,0.630017827,0.9
+47,0.349368861,0.291566007
+48,0.516054417,0
+49,0.537368223,0.750354989
+50,0.247883564,0.460734633
+51,0.875667702,0.638270293
+52,0.720106259,0.323351706
+53,0.851599153,0.730568278
+54,0.81586188,0.500694437
+55,0.578319983,0.9
+56,0.837499388,0.786739067
+57,0.170794002,0.794520449
+58,0.25678629,0.358456355
+59,0.136181831,0.410947679
+60,0.360264265,0.211206668
+61,0.410941832,0.9
+62,0.317079225,0.867807476
+63,0.762990007,0.669498753
+64,0.385402661,0.9
+65,0.324747608,0.511773829
+66,0.534156867,0.502118079
+67,0.21273938,0.184432318
+68,0.741757585,0.475490718
+69,0.159640515,0.412015329
+70,0.889509549,0
+71,0.717795815,0.56685373
+72,0.258972545,0.119850179
+73,0.104417694,0.601998996
+74,0.752369143,0.384311164
+75,0.665485875,0.778347438
+76,0.683205734,0.762472597
+77,0.717016277,0.424425195
+78,0.159235721,0.856911245
+79,0.386772583,0.395786315
+80,0.192695248,0.648379783
+81,0.790482741,0.568188553
+82,0.598638501,0.429019006
+83,0.36471842,0.350370788
+84,0.15084668,0.70238253
+85,0.348785857,0.617004973
+86,0.360146658,0.579820975
+87,0.683684943,0.9
+88,0.610045977,0
+89,0.809770194,0.898989765
+90,0.47777194,0.6383925
+91,0.195675397,0.834275071
+92,0.67059583,0.732810268
+93,0.708628039,0.320591054
+94,0.549021758,0.617227583
+95,0.716773744,0.237749783
+96,0.495036477,0.487654925
+97,0.518186264,0.57323548
+98,0.442032815,0.89654152
+99,0.120335301,0.868575872
+100,0.186313142,0.461549286
+101,0.125143349,0.194870217
+102,0.609128329,0.786990531
+103,0.351484785,0.891649669
+104,0.506856553,0.768351474
+105,0.826053179,0.9
+106,0.299433783,0.568515583
+107,0.428306338,0.165357974
+108,0.704440911,0.9
+109,0.283038532,0.9
+110,0.161583928,0.193599593
+111,0.331801162,0.222202775
+112,0.22897703,0.127596961
+113,0.843758122,0.603302728
+114,0.746496304,0.523862523
+115,0.606723005,0.32452639
+116,0.797168472,0.437875236
+117,0.742937662,0.383344477
+118,0.249256047,0.9
+119,0.814047199,0.252747009
+120,0.531473794,0.111905834
+121,0.745952124,0.713058927
+122,0.81687304,0.633918652
+123,0.35440278,0.9
+124,0.18804154,0.667032742
+125,0.28234813,0.9
+126,0.441686231,0.9
+127,0.754411813,0.419167132
+128,0.788584467,0.318857492
+129,0.105561704,0.499083336
+130,0.508597842,0.301754125
+131,0.433928803,0.452810626
+132,0.277686248,0.577790408
+133,0.195892294,0
+134,0.370092137,0.573066409
+135,0.854327763,0.530452687
+136,0.358562346,0.211194602
+137,0.515032497,0.851787499
+138,0.662415167,0.431390978
+139,0.390903682,0.631142712
+140,0.877425666,0.455200314
+141,0.869957836,0.9
+142,0.301425837,0.041752446
+143,0.497798805,0.674007817
+144,0.340702648,0.9
+145,0.327872396,0.063539785
+146,0.129509558,0.633467746
+147,0.587651467,0.86641778
+148,0.502143219,0.671656913
+149,0.141183001,0.868122908
+150,0.322917171,0.9
+151,0.826612709,0.825370749
+152,0.291649513,0.9
+153,0.215915898,0.760431834
+154,0.491562208,0.583798204
+155,0.888520363,0.763032528
+156,0.293644217,0.9
+157,0.637708438,0.193725648
+158,0.709295692,0.561064281
+159,0.290110035,0.9
+160,0.682573079,0.093302535
+161,0.394226506,0.217486014
+162,0.605844664,0.414951313
+163,0.606823769,0.234263037
+164,0.528619747,0.672173284
+165,0.172231816,0.311602999
+166,0.768241996,0.801998539
+167,0.356624052,0.9
+168,0.249214808,0.397102594
+169,0.132620113,0.233385147
+170,0.572714355,0.264743837
+171,0.642051489,0.778244155
+172,0.113270263,0.9
+173,0.509674447,0.371591146
+174,0.28119662,0.579338394
+175,0.616138232,0.473213701
+176,0.239493143,0.734002753
+177,0.65275019,0.815698144
+178,0.409388277,0.64513043
+179,0.849383991,0.652955826
+180,0.210016755,0.445684064
+181,0.372853081,0.865538702
+182,0.190778817,0.297702787
+183,0.839754895,0.80608299
+184,0.801871483,0.441544832
+185,0.306353302,0
+186,0.627987237,0.582832059
+187,0.75377776,0.887885476
+188,0.544160649,0.58192299
+189,0.523720463,0.314658549
+190,0.293481833,0.62433224
+191,0.174482214,0.171393522
+192,0.817772606,0.856205944
+193,0.820334446,0.144868162
+194,0.606481166,0.65632466
+195,0.371223833,0.380393034
+196,0.37936766,0.9
+197,0.680764543,0.9
+198,0.817688208,0.9
+199,0.809669139,0.023913392
+200,0.723900437,0.373537822
+201,0.613625317,0.543091636
+202,0.167311972,0
+203,0.229302971,0.245499491
+204,0.818843351,0.702302812
+205,0.585143248,0.456552424
+206,0.107357641,0.9
+207,0.181177234,0.9
+208,0.630801415,0.785450778
+209,0.104049267,0.728892465
+210,0.228646441,0.9
+211,0.538987031,0.459803452
+212,0.653516158,0.060618166
+213,0.621569008,0.169383435
+214,0.279415448,0.52503599
+215,0.669743377,0.9
+216,0.28979927,0.232644237
+217,0.360319759,0.196706038
+218,0.697193124,0.782270786
+219,0.619706319,0.634509583
+220,0.779378728,0.742370382
+221,0.626090314,0.705028509
+222,0.554646883,0.269498177
+223,0.174939814,0.260250194
+224,0.394172642,0.524887108
+225,0.312161894,0.282839581
+226,0.295191715,0.601561559
+227,0.878408444,0.310749962
+228,0.41447818,0.146266917
+229,0.813637244,0.535602752
+230,0.604910901,0.406690812
+231,0.735849043,0.439099269
+232,0.502109674,0.473977676
+233,0.561523108,0.291093701
+234,0.494014155,0
+235,0.25619439,0.544031191
+236,0.677961692,0.206781974
+237,0.32461789,0.871280227
+238,0.119452773,0.813680537
+239,0.616377837,0.405761625
+240,0.241688544,0.277176932
+241,0.852366867,0.754865335
+242,0.863142862,0.889112501
+243,0.831891512,0.770036633
+244,0.39612696,0.58783425
+245,0.112365293,0.629055709
+246,0.84265485,0.401969793
+247,0.442547319,0.473997687
+248,0.873323855,0.131348856
+249,0.870895982,0.9
+250,0.782407564,0.578155048
+251,0.335559114,0.560128141
+252,0.408078183,0.106789283
+253,0.780909337,0
+254,0.353537604,0
+255,0.235594197,0.715233893
+256,0.54544101,0.571425972
+257,0.848923819,0
+258,0.656823837,0.717035216
+259,0.556048936,0.030601887
+260,0.177741195,0.602275375
+261,0.592005781,0.718249881
+262,0.89204308,0.9
+263,0.212067212,0.281156905
+264,0.514663722,0.241378063
+265,0.801898458,0
+266,0.692614894,0
+267,0.657612593,0.361212285
+268,0.661987267,0.237156186
+269,0.387592921,0.547202197
+270,0.334873475,0.352543034
+271,0.747488924,0.599771513
+272,0.748090716,0.625597273
+273,0.793657855,0.766044459
+274,0.830592442,0.242180223
+275,0.509073919,0.211805788
+276,0.501213036,0.536677238
+277,0.738636143,0.26898898
+278,0.619971145,0.89404248
+279,0.661573502,0.39105004
+280,0.736634136,0.557414556
+281,0.812004273,0.832808746
+282,0.370396125,0.733753018
+283,0.400466362,0.394609603
+284,0.175185552,0.198192559
+285,0.562624113,0.075237495
+286,0.128753819,0.541309241
+287,0.472478415,0.161985702
+288,0.534115708,0.328472331
+289,0.329233002,0.094428109
+290,0.572666608,0
+291,0.1244002,0.280357394
+292,0.129878551,0.229383829
+293,0.758080449,0.593996777
+294,0.388152513,0.39465319
+295,0.20164841,0.9
+296,0.517794608,0.043576483
+297,0.715994842,0.476350366
+298,0.272656822,0.290452863
+299,0.598312381,0.447587372
+300,0.168277972,0.9
+301,0.141345377,0
+302,0.525083705,0.9
+303,0.532508097,0.391722606
+304,0.609943921,0.365382016
+305,0.680873067,0.9
+306,0.880681664,0.73426367
+307,0.513040279,0.743442953
+308,0.358365178,0.806462926
+309,0.736148956,0.337982969
+310,0.316665801,0.9
+311,0.451177137,0.362464057
+312,0.162765105,0.378720332
+313,0.120280595,0.864158962
+314,0.870118732,0.338215219
+315,0.768784096,0.719991179
+316,0.656779365,0.89653844
+317,0.427162356,0.248380521
+318,0.238635456,0.582568045
+319,0.225149634,0
+320,0.300194319,0.09455141
+321,0.539381332,0.220674016
+322,0.671676738,0.422550877
+323,0.628157901,0.9
+324,0.323947118,0.624292143
+325,0.863892225,0.740150198
+326,0.690317533,0.317211165
+327,0.543483242,0
+328,0.589376597,0.530291289
+329,0.43568005,0.868179129
+330,0.298184792,0.9
+331,0.384778143,0.235703623
+332,0.706276888,0.527245358
+333,0.111514791,0.276162354
+334,0.192858112,0.9
+335,0.136802114,0.67743365
+336,0.132583042,0.72627581
+337,0.784368467,0.141174124
+338,0.662926288,0.640569526
+339,0.479339063,0.294329789
+340,0.178267329,0.126127569
+341,0.4932927,0.197049838
+342,0.478777417,0.442695914
+343,0.238561496,0.772527265
+344,0.447081319,0.589232498
+345,0.418803788,0.629466201
+346,0.592680078,0.84005646
+347,0.608074921,0.516977856
+348,0.136243208,0.322960931
+349,0.399690092,0.9
+350,0.600687933,0.048632481
+351,0.502509007,0.9
+352,0.785191873,0.655350875
+353,0.626954905,0.424066799
+354,0.230347542,0.79213536
+355,0.156454998,0.096616115
+356,0.613935423,0.517046723
+357,0.121209048,0.52208024
+358,0.568620465,0.473112515
+359,0.852184193,0.754590988
+360,0.560379342,0.9
+361,0.410535941,0.9
+362,0.614630575,0.39374087
+363,0.466602312,0.148108833
+364,0.536493431,0.469579726
+365,0.853171847,0.48954448
+366,0.40888211,0.050042249
+367,0.868952451,0.630624017
+368,0.824280514,0.709203372
+369,0.256632908,0
+370,0.155489041,0.477012224
+371,0.180622401,0.608930319
+372,0.114577461,0.304593278
+373,0.175554369,0.9
+374,0.646405419,0.263976137
+375,0.156950919,0
+376,0.355180504,0.725098866
+377,0.775900249,0.731484113
+378,0.118617549,0.9
+379,0.751574786,0.079999297
+380,0.32548382,0.698535487
+381,0.194531862,0.114491484
+382,0.657389732,0.386378141
+383,0.603154277,0.9
+384,0.801977611,0
+385,0.688056835,0.688824247
+386,0.742784744,0.477075344
+387,0.325627658,0.9
+388,0.241951635,0.229194717
+389,0.700491801,0.9
+390,0.745467791,0.365119491
+391,0.892404114,0.356122106
+392,0.430094142,0.072999329
+393,0.397614469,0.391199297
+394,0.721130369,0.423416575
+395,0.372642832,0.46387764
+396,0.84460586,0.755790989
+397,0.786730201,0.726222582
+398,0.443195222,0.286122987
+399,0.700696854,0.150457872
+400,0.703634299,0.9
+401,0.182499095,0.007200451
+402,0.822042325,0.070653788
+403,0.504201898,0
+404,0.761165973,0.9
+405,0.356039681,0.097125069
+406,0.816418583,0.9
+407,0.411361343,0.9
+408,0.108670121,0.800345851
+409,0.824305581,0.554559991
+410,0.173029341,0.866005543
+411,0.35545091,0.394953575
+412,0.860049574,0.350839592
+413,0.860485718,0.454700806
+414,0.55875031,0.168064655
+415,0.60546977,0.475601017
+416,0.458756418,0.811466233
+417,0.334568617,0.082747762
+418,0.362931636,0.481130455
+419,0.638014765,0.610148403
+420,0.701899624,0.112002855
+421,0.733263235,0.516900078
+422,0.731694514,0.554471896
+423,0.172964882,0.128581098
+424,0.495536244,0.121544947
+425,0.146047008,0.9
+426,0.539623106,0.9
+427,0.453224401,0
+428,0.810163346,0.9
+429,0.38073201,0.368381767
+430,0.193653613,0.449430094
+431,0.214393346,0.307112578
+432,0.709208505,0.728075191
+433,0.594574451,0.729358526
+434,0.180898141,0.761762761
+435,0.167285445,0.392994951
+436,0.660775305,0.253023444
+437,0.158210405,0.185973554
+438,0.757488047,0.771725246
+439,0.664993782,0.461585143
+440,0.165079025,0.827318779
+441,0.167870171,0.9
+442,0.889311663,0.352196534
+443,0.399416637,0.725943746
+444,0.396513718,0.722537735
+445,0.750239654,0.787883489
+446,0.857798862,0.021251169
+447,0.888800851,0.613334021
+448,0.702702548,0.584266571
+449,0.401007668,0.686896807
+450,0.166800573,0.610468755
+451,0.721717533,0.299634831
+452,0.5467234,0.51728741
+453,0.439377607,0.321720321
+454,0.825083508,0.609811224
+455,0.188957986,0.124611017
+456,0.494100083,0.640486799
+457,0.109082916,0.816432818
+458,0.474928514,0.875603243
+459,0.145042621,0
+460,0.195054333,0.436427182
+461,0.194020997,0.222805937
+462,0.619368242,0.386010606
+463,0.696835903,0.392643135
+464,0.566695012,0.577819709
+465,0.869738039,0.83340227
+466,0.399896464,0
+467,0.328569669,0.9
+468,0.794879303,0.11571177
+469,0.278876671,0.811585918
+470,0.870578032,0.795252622
+471,0.10972358,0.893777658
+472,0.875903061,0.363554268
+473,0.13452793,0.04793441
+474,0.812914491,0.469274644
+475,0.522160887,0.811754325
+476,0.894371837,0.9
+477,0.159037252,0.798691607
+478,0.543083428,0.586919061
+479,0.875442028,0.9
+480,0.518478275,0.205080102
+481,0.603518911,0.873356815
+482,0.656598951,0.322534784
+483,0.463632852,0.800643755
+484,0.602046464,0.794521938
+485,0.56745145,0.457772656
+486,0.820926408,0.265928321
+487,0.136357104,0.410544575
+488,0.324770552,0.214104789
+489,0.860329187,0.237168198
+490,0.812211027,0.356634289
+491,0.464525402,0.159013205
+492,0.596106078,0.436690151
+493,0.321904946,0.076210719
+494,0.250496928,0.438814406
+495,0.470958724,0.582810641
+496,0.382681782,0.632245159
+497,0.566924889,0.513618598
+498,0.16218771,0.509592906
+499,0.879515846,0.61010319
+500,0.888968596,0.573884366
+501,0.658529371,0.350736306
+502,0.528877093,0.407413995
+503,0.347622093,0
+504,0.751036016,0.168183797
+505,0.647784938,0.285101277
+506,0.230093551,0.63765552
+507,0.828741748,0.629778228
+508,0.758029794,0.575279515
+509,0.859839931,0.799048565
+510,0.680575607,0.677563662
+511,0.590732157,0.848004803
+512,0.434594429,0.648693023
+513,0.846182787,0.9
+514,0.792851112,0
+515,0.136174936,0
+516,0.12109358,0.072480509
+517,0.401170694,0.9
+518,0.748442665,0.9
+519,0.889820903,0.536135208
+520,0.220333513,0.9
+521,0.575304572,0.17037831
+522,0.404712685,0.896877748
+523,0.875931518,0.226885176
+524,0.773695139,0.102118449
+525,0.770662964,0.642640195
+526,0.474954528,0.606392363
+527,0.431855602,0.293036753
+528,0.318725658,0.233284656
+529,0.145100397,0.742552708
+530,0.791777901,0.681630709
+531,0.750320807,0
+532,0.899774139,0.014221788
+533,0.89730947,0.535286327
+534,0.544345364,0.012921094
+535,0.715189932,0.303804232
+536,0.855812584,0.160563795
+537,0.779717913,0.131607377
+538,0.297878481,0.9
+539,0.460435308,0.326836869
+540,0.203327532,0.595249297
+541,0.863240822,0.822788795
+542,0.584939708,0
+543,0.282914244,0.813627723
+544,0.637360548,0.286309155
+545,0.594502592,0.9
+546,0.386530174,0.218872209
+547,0.190846074,0.356354348
+548,0.637258556,0.744653648
+549,0.516246161,0.228832408
+550,0.717854713,0.381008212
+551,0.516130801,0.643706903
+552,0.7817452,0.862648152
+553,0.541525471,0.457998114
+554,0.548750377,0.9
+555,0.801322882,0.057308634
+556,0.422786293,0.429233853
+557,0.207212183,0.506630172
+558,0.123026141,0.579619634
+559,0.704109805,0.635860542
+560,0.596247641,0.779320272
+561,0.663263814,0.392966897
+562,0.270371329,0.038949583
+563,0.20909718,0.9
+564,0.111635733,0.191541437
+565,0.380470047,0.700941476
+566,0.571934149,0.190403259
+567,0.413795236,0
+568,0.449979938,0.12867131
+569,0.823326956,0.9
+570,0.378604374,0.657565215
+571,0.511191591,0.564471676
+572,0.72692241,0.168688659
+573,0.417234226,0.695115469
+574,0.59766936,0.9
+575,0.789890967,0
+576,0.859616499,0.455152068
+577,0.217658785,0.297756198
+578,0.8412701,0.793123632
+579,0.493693034,0.695294164
+580,0.306595511,0.542262095
+581,0.467308605,0.453772986
+582,0.88402606,0.56067833
+583,0.494094475,0.48707089
+584,0.363001288,0.354013044
+585,0.606720683,0.9
+586,0.292116495,0.59640684
+587,0.160690662,0.346338874
+588,0.203103778,0.056573698
+589,0.202436671,0.483749902
+590,0.221522155,0.686800138
+591,0.211061738,0.697284337
+592,0.612699796,0.9
+593,0.245504068,0.146914868
+594,0.376533827,0.555753579
+595,0.817430728,0.279245059
+596,0.479169312,0.355585277
+597,0.634046191,0.293514843
+598,0.237855897,0
+599,0.253831215,0.124562999
+600,0.132694893,0.9
+601,0.23514805,0.258715482
+602,0.322872271,0.416372476
+603,0.241608387,0
+604,0.170962027,0.229906693
+605,0.196508697,0.061739979
+606,0.468623014,0.435819059
+607,0.265066975,0.474501
+608,0.391415889,0.879707971
+609,0.502733817,0.009105176
+610,0.652315863,0.593635726
+611,0.131449712,0.9
+612,0.739528319,0.9
+613,0.602320312,0.9
+614,0.165407226,0.105693455
+615,0.798862899,0.163687153
+616,0.83669792,0.321195099
+617,0.148862368,0.836806524
+618,0.321502119,0.746060945
+619,0.744961024,0.793060363
+620,0.698607752,0.665532652
+621,0.247616815,0.392202609
+622,0.267479459,0.186053372
+623,0.396377682,0.341051727
+624,0.487618388,0.9
+625,0.594603817,0
+626,0.395130912,0.698189057
+627,0.470027773,0.766648506
+628,0.697976751,0.530362109
+629,0.129346562,0.129831401
+630,0.301949555,0.370935393
+631,0.670679669,0.659832743
+632,0.81616547,0.721269338
+633,0.509341954,0.078963902
+634,0.525690788,0.9
+635,0.185737609,0.485752967
+636,0.457929893,0.221050583
+637,0.526093813,0.312141628
+638,0.293976403,0.369071128
+639,0.315394585,0.494455714
+640,0.40182733,0.9
+641,0.116056958,0.9
+642,0.357663332,0.432833134
+643,0.269158406,0.564192924
+644,0.361997882,0.433373006
+645,0.195809705,0.277771347
+646,0.812421825,0.709003281
+647,0.574873963,0.04179906
+648,0.643281855,0.882822175
+649,0.731336991,0.9
+650,0.498753759,0.61926981
+651,0.16953623,0.30886779
+652,0.529685233,0.019184445
+653,0.569472894,0.071380962
+654,0.696351579,0.506210695
+655,0.445327637,0.541143205
+656,0.202064242,0.9
+657,0.327020725,0.464777285
+658,0.390465837,0.3442423
+659,0.616733793,0.10498328
+660,0.556622644,0.608890864
+661,0.384877381,0.801058732
+662,0.889212199,0.399520959
+663,0.584619855,0.718003042
+664,0.289781433,0.564040344
+665,0.181425978,0.784546478
+666,0.222287311,0.764606813
+667,0.296766183,0.791738859
+668,0.228545099,0.782719747
+669,0.249253619,0.10350808
+670,0.328076135,0.592074315
+671,0.238698876,0.590546628
+672,0.81741234,0.757073413
+673,0.164186997,0.632102093
+674,0.519609112,0.9
+675,0.428317462,0.9
+676,0.885902894,0.19363742
+677,0.189631122,0
+678,0.418284479,0.674262565
+679,0.875576347,0.067662156
+680,0.792405701,0.853617271
+681,0.753657657,0
+682,0.306322262,0.9
+683,0.23671007,0.30998468
+684,0.634914576,0.9
+685,0.843500791,0.209588005
+686,0.545410314,0.551126731
+687,0.557290152,0.736446674
+688,0.323983275,0.661229149
+689,0.715594347,0.611475963
+690,0.249634999,0.857951086
+691,0.358943389,0.733981048
+692,0.440349151,0.110992458
+693,0.506088303,0.823233566
+694,0.293927786,0.243188178
+695,0.19186946,0.169331526
+696,0.588496034,0
+697,0.330904443,0.073369428
+698,0.564990577,0.438545559
+699,0.223490172,0.838604809
+700,0.484912081,0.9
+701,0.526071546,0.509863806
+702,0.141458829,0.442976066
+703,0.369283423,0.036354545
+704,0.207531742,0.595821461
+705,0.150699976,0.673331198
+706,0.891968186,0.079341299
+707,0.357883076,0
+708,0.747899557,0.322567583
+709,0.303712524,0.704855002
+710,0.645202178,0.721234563
+711,0.708182288,0.53056543
+712,0.576510992,0
+713,0.477260951,0.894663295
+714,0.429472731,0.765967217
+715,0.379094613,0
+716,0.843623315,0.9
+717,0.764495526,0.020179491
+718,0.872021529,0.635647515
+719,0.199437779,0.9
+720,0.68469398,0.169536942
+721,0.850672365,0.044872475
+722,0.244986453,0.205646056
+723,0.153197014,0.070808633
+724,0.692896519,0
+725,0.559578491,0.823572394
+726,0.773463021,0
+727,0.211817901,0.674115828
+728,0.736213849,0.9
+729,0.261301856,0.319724533
+730,0.230924754,0.422784388
+731,0.231412638,0.643530247
+732,0.751659776,0.353825286
+733,0.632157777,0.405532106
+734,0.51845234,0.55638193
+735,0.387064387,0.400415929
+736,0.801760433,0.746398651
+737,0.413956086,0.31045017
+738,0.753279552,0.611290475
+739,0.451307927,0.828932397
+740,0.401555544,0.676018315
+741,0.470143829,0.783359852
+742,0.341102299,0.484825074
+743,0.698087504,0.507832813
+744,0.502176312,0.239453538
+745,0.285770156,0.537522754
+746,0.819659659,0.83547497
+747,0.407112977,0.277966345
+748,0.534842289,0
+749,0.825177689,0.9
+750,0.599390397,0
+751,0.193518433,0.432255287
+752,0.851865699,0.334711549
+753,0.602166442,0.608613492
+754,0.367924492,0.9
+755,0.211417658,0.9
+756,0.735220151,0.695430535
+757,0.596058205,0.9
+758,0.526768874,0.712197092
+759,0.815114066,0.107622053
+760,0.730877769,0.9
+761,0.221339904,0.521019557
+762,0.349377654,0.899921438
+763,0.298791312,0.344947128
+764,0.695157034,0.595989562
+765,0.126825948,0.429774057
+766,0.555911748,0.205427445
+767,0.709966949,0.550310223
+768,0.801412509,0.205775945
+769,0.373665399,0.510585936
+770,0.757005844,0.610315149
+771,0.18850539,0.582000631
+772,0.777161833,0.9
+773,0.20199093,0.812268746
+774,0.417829832,0.9
+775,0.737836293,0.45659749
+776,0.219933942,0.255550591
+777,0.283401116,0.824392204
+778,0.677802055,0.662358027
+779,0.676029229,0.230244761
+780,0.612918106,0.754797451
+781,0.655158756,0
+782,0.534179555,0.732152294
+783,0.301439247,0.691777763
+784,0.376556795,0.753562435
+785,0.245278173,0.752649568
+786,0.826760449,0.828537614
+787,0.566713436,0.611101535
+788,0.420681133,0.426066583
+789,0.469604643,0.328028737
+790,0.857826672,0.619969654
+791,0.222681122,0.343139913
+792,0.568983866,0.558438304
+793,0.504710943,0
+794,0.589163388,0.9
+795,0.114488147,0.013628956
+796,0.797699127,0
+797,0.845694626,0.846428438
+798,0.552106547,0.059664309
+799,0.657320659,0.421989478
+800,0.837999505,0.263938268
+801,0.665790907,0.9
+802,0.222031234,0.34851776
+803,0.561030688,0.685587123
+804,0.585372037,0.402541098
+805,0.439304537,0.287443299
+806,0.689155388,0.755569942
+807,0.847493612,0.185037681
+808,0.84045481,0.350319657
+809,0.460671497,0
+810,0.190590437,0
+811,0.887872959,0.247652379
+812,0.771118469,0.9
+813,0.199730145,0.154721294
+814,0.836673506,0.500187896
+815,0.79591709,0.031786968
+816,0.515070446,0.447448538
+817,0.573020349,0.057224712
+818,0.419202163,0.9
+819,0.143809311,0.560756311
+820,0.368157793,0.268479888
+821,0.742282759,0.304554366
+822,0.103705618,0.322554819
+823,0.366799337,0.871360078
+824,0.418534955,0.9
+825,0.529916482,0.525181241
+826,0.835884493,0.192729785
+827,0.377076795,0.030194688
+828,0.377562562,0.9
+829,0.690000998,0.498031622
+830,0.461774353,0.094969901
+831,0.279683858,0.9
+832,0.461951613,0.569342184
+833,0.212685616,0.574137375
+834,0.241109589,0.50883471
+835,0.498694218,0.691815652
+836,0.43514036,0.3941246
+837,0.831876721,0.4250262
+838,0.389915119,0.629426338
+839,0.56447068,0.380919947
+840,0.60581143,0.047314774
+841,0.110475565,0.023601305
+842,0.630829898,0.283155523
+843,0.242428773,0.430664499
+844,0.868856254,0.227940361
+845,0.218930182,0.623995717
+846,0.431699299,0.041564826
+847,0.168279734,0.249017933
+848,0.897499401,0.275312476
+849,0.501756008,0.629105532
+850,0.576308014,0.660853868
+851,0.153661182,0.19205541
+852,0.699968376,0.684843774
+853,0.267924474,0.9
+854,0.818443432,0.9
+855,0.264111712,0.510245918
+856,0.252550177,0.509225921
+857,0.129239734,0.9
+858,0.477653556,0.181365776
+859,0.551872907,0.9
+860,0.152566912,0.9
+861,0.720422093,0.440521756
+862,0.462631068,0.395553765
+863,0.519512215,0.496358382
+864,0.452610198,0.603895363
+865,0.420610449,0.9
+866,0.547712265,0.9
+867,0.224192197,0.232212969
+868,0.245542504,0
+869,0.789428497,0.467212445
+870,0.85689237,0.9
+871,0.398647453,0.696880578
+872,0.316595739,0.259939856
+873,0.615199635,0.121905279
+874,0.426987337,0.9
+875,0.120309085,0.829255596
+876,0.224922078,0.51824201
+877,0.672777783,0.853366492
+878,0.627139154,0.42316913
+879,0.121676794,0.479190243
+880,0.27757773,0.29710151
+881,0.284859837,0.645220204
+882,0.637514195,0.755069768
+883,0.11576843,0.665360064
+884,0.183286866,0.616515497
+885,0.739932868,0.195189159
+886,0.24283573,0.675757772
+887,0.622196886,0
+888,0.290546225,0
+889,0.179553114,0.9
+890,0.294537753,0.9
+891,0.677813545,0
+892,0.784557174,0.593622404
+893,0.764175892,0.614313082
+894,0.417746824,0.329100312
+895,0.634468109,0.617623992
+896,0.263987436,0.627855087
+897,0.334518184,0.396846944
+898,0.817068655,0.077784525
+899,0.110401539,0.155259676
+900,0.168406825,0.519077876
+901,0.266309004,0.526586639
+902,0.121225763,0
+903,0.245148348,0.879305624
+904,0.566433249,0.500060623
+905,0.43713964,0.551573716
+906,0.814137369,0.321835573
+907,0.753954849,0.9
+908,0.373453881,0.512353169
+909,0.307538747,0.38053411
+910,0.403753927,0.404781045
+911,0.572235954,0.465045611
+912,0.314450913,0.491905004
+913,0.599319126,0.9
+914,0.427529322,0.616470334
+915,0.541637745,0.268066979
+916,0.448901223,0.687141209
+917,0.335572608,0.9
+918,0.858762646,0.522107012
+919,0.710884635,0.68146507
+920,0.212090541,0.9
+921,0.794774381,0.459998009
+922,0.489944959,0
+923,0.815641782,0.671626119
+924,0.739884205,0.564785035
+925,0.440170804,0.677641272
+926,0.117975447,0.537707678
+927,0.314941888,0.235910364
+928,0.533307372,0.658007968
+929,0.606782576,0.462395216
+930,0.306310148,0.581727352
+931,0.211484859,0.9
+932,0.767944189,0.357523523
+933,0.887521745,0.411138792
+934,0.520552146,0.797687105
+935,0.237343429,0.544391687
+936,0.317845861,0.732638395
+937,0.114712541,0.322203681
+938,0.831439045,0.280121239
+939,0.194200866,0.495145109
+940,0.56121318,0
+941,0.319244177,0.023560038
+942,0.543342402,0.728298656
+943,0.621136311,0.413790858
+944,0.763793443,0.869446044
+945,0.265137017,0.661151239
+946,0.108796663,0.443875203
+947,0.209508504,0.649752172
+948,0.820014913,0.302974845
+949,0.799112062,0.505207452
+950,0.577930482,0.689261658
+951,0.580413488,0.088053248
+952,0.63202934,0.123430379
+953,0.240297023,0.307292604
+954,0.831529557,0.482177859
+955,0.43501642,0.9
+956,0.406510823,0.9
+957,0.515134164,0.276283568
+958,0.137572773,0.106383953
+959,0.233026695,0.729408407
+960,0.690426893,0.865337494
+961,0.166238934,0.331889912
+962,0.582521688,0.364184963
+963,0.296279288,0.740478264
+964,0.411436491,0.489036243
+965,0.330954989,0.578971069
+966,0.384538173,0.015390396
+967,0.675236724,0.190131095
+968,0.337697372,0.176936745
+969,0.553123712,0.411411886
+970,0.480840322,0.867272117
+971,0.630936932,0.211223827
+972,0.849463791,0.686975213
+973,0.686057678,0.548907023
+974,0.271952303,0.635134985
+975,0.124946508,0.444004081
+976,0.309811235,0.9
+977,0.576062345,0.821573298
+978,0.141140651,0.161003341
+979,0.497092998,0.9
+980,0.577474279,0.541951571
+981,0.367395113,0.387759296
+982,0.716729763,0.51244302
+983,0.185278603,0.362207806
+984,0.160110225,0.412602619
+985,0.682551005,0.450738158
+986,0.496393053,0.394094822
+987,0.650721917,0.370922101
+988,0.447861871,0.51090245
+989,0.297121627,0.272085598
+990,0.755281854,0.368980355
+991,0.739532703,0.658156057
+992,0.655757177,0.150005837
+993,0.31771611,0.9
+994,0.572184533,0.316523222
+995,0.388779118,0.356695694
+996,0.173265659,0.484370624
+997,0.83385086,0.9
+998,0.209454905,0.677277106
+999,0.860189883,0
+1000,0.456804618,0

A2 #Q7 Chrf Scores CSV.csv

@@ -0,0 +1,1001 @@
+Sample,CHRF LTSM  Score,CHRFSeq2seq Score
+1,0.318066158,0.818785258
+2,0.542299349,1.043018449
+3,0,0.5007191
+4,0.514403292,1.015122392
+5,0.750750751,1.251469851
+6,1.108281456,1.609000556
+7,0,0.5007191
+8,0.77650713,1.27722623
+9,0.258799172,0.759518272
+10,0.990990991,1.491710091
+11,0.412541254,0.913260354
+12,0.879507476,1.380226576
+13,0.338753388,0.839472488
+14,0.499001996,0.999721096
+15,0.727449079,1.228168179
+16,0,0.5007191
+17,1.556016598,2.056735698
+18,0.828363154,1.329082254
+19,0.375375375,0.876094475
+20,0.417262756,0.917981856
+21,1.068376068,1.569095168
+22,0.825082508,1.325801608
+23,0.255623722,0.756342822
+24,1.086956522,1.587675622
+25,1.47325476,1.97397386
+26,0.333333333,0.834052433
+27,0.656167979,1.156887079
+28,0.661375661,1.162094761
+29,1.001780944,1.502500044
+30,0.322997416,0.823716516
+31,0.712250712,1.212969812
+32,0.262054507,0.762773607
+33,0.265392781,0.766111881
+34,0,0.5007191
+35,0.465549348,0.966268448
+36,0.542727452,1.043446552
+37,0.656167979,1.156887079
+38,1.1684427,1.6691618
+39,0.850340136,1.351059236
+40,0.39184953,0.89256863
+41,0.19379845,0.69451755
+42,0.621890547,1.122609647
+43,0.813599224,1.314318324
+44,1.163873371,1.664592471
+45,0.27593819,0.77665729
+46,0.368731563,0.869450663
+47,0.607385811,1.108104911
+48,0.647668394,1.148387494
+49,0.564130337,1.064849437
+50,0.591016548,1.091735648
+51,0.503524673,1.004243773
+52,0.344352617,0.845071717
+53,0.983168161,1.483887261
+54,0.356125356,0.856844456
+55,0.666666667,1.167385767
+56,1.201460977,1.702180077
+57,0.322997416,0.823716516
+58,1.59642401,2.09714311
+59,1.086956522,1.587675622
+60,0.886524823,1.387243923
+61,0.645994832,1.146713932
+62,0.694676003,1.195395103
+63,0.816993464,1.317712564
+64,1.185266229,1.685985329
+65,0.468164794,0.968883894
+66,0.698324022,1.199043122
+67,0.768757688,1.269476788
+68,0.287356322,0.788075422
+69,0.897601609,1.398320709
+70,0.499001996,0.999721096
+71,1.033057851,1.533776951
+72,0.862068966,1.362788066
+73,1.351351351,1.852070451
+74,0.117370892,0.618089992
+75,0.268817204,0.769536304
+76,0.631121882,1.131840982
+77,0.255623722,0.756342822
+78,0.668377714,1.169096814
+79,0.570776256,1.071495356
+80,0,0.5007191
+81,0.338753388,0.839472488
+82,0.295508274,0.796227374
+83,0.727348296,1.228067396
+84,0.164690382,0.665409482
+85,0,0.5007191
+86,0.968992248,1.469711348
+87,0,0.5007191
+88,0.881834215,1.382553315
+89,1.375137514,1.875856614
+90,0.813449024,1.314168124
+91,0.559284116,1.060003216
+92,1.094276094,1.594995194
+93,0.677506775,1.178225875
+94,1.122874559,1.623593659
+95,0,0.5007191
+96,0.258799172,0.759518272
+97,0,0.5007191
+98,0.730994152,1.231713252
+99,0.605796259,1.106515359
+100,0.796178344,1.296897444
+101,1.226692836,1.727411936
+102,0.322997416,0.823716516
+103,0.537634409,1.038353509
+104,0.373692078,0.874411178
+105,0.838926174,1.339645274
+106,0.732747136,1.233466236
+107,0.559284116,1.060003216
+108,0.265392781,0.766111881
+109,0.759301443,1.260020543
+110,0.295508274,0.796227374
+111,0.717154332,1.217873432
+112,0.338753388,0.839472488
+113,1.109262341,1.609981441
+114,1.003379806,1.504098906
+115,0.559284116,1.060003216
+116,1.034612491,1.535331591
+117,1.126126126,1.626845226
+118,0.235404896,0.736123996
+119,0.900900901,1.401620001
+120,0.592417062,1.093136162
+121,0,0.5007191
+122,0.887705282,1.388424382
+123,0.626566416,1.127285516
+124,0,0.5007191
+125,0.809061489,1.309780589
+126,0.279642058,0.780361158
+127,0,0.5007191
+128,0,0.5007191
+129,0,0.5007191
+130,0.768049155,1.268768255
+131,0.998003992,1.498723092
+132,1.159554731,1.660273831
+133,0.299760192,0.800479292
+134,0.888749477,1.389468577
+135,0.574712644,1.075431744
+136,0.599520384,1.100239484
+137,0.420875421,0.921594521
+138,0,0.5007191
+139,1.033591731,1.534310831
+140,0,0.5007191
+141,0.382262997,0.882982097
+142,0.313283208,0.814002308
+143,1.073619632,1.574338732
+144,0,0.5007191
+145,0.262054507,0.762773607
+146,0,0.5007191
+147,0,0.5007191
+148,0,0.5007191
+149,0.262054507,0.762773607
+150,0.32808399,0.82880309
+151,0.32808399,0.82880309
+152,0.268817204,0.769536304
+153,0,0.5007191
+154,0,0.5007191
+155,0.782472613,1.283191713
+156,0.9499924,1.4507115
+157,0.457875458,0.958594558
+158,0.683060109,1.183779209
+159,0.669344043,1.170063143
+160,0,0.5007191
+161,0,0.5007191
+162,0.642673522,1.143392622
+163,0.754527163,1.255246263
+164,0.287356322,0.788075422
+165,0.641025641,1.141744741
+166,0.356125356,0.856844456
+167,0,0.5007191
+168,0.721126111,1.221845211
+169,0.683060109,1.183779209
+170,0.524109015,1.024828115
+171,0.382262997,0.882982097
+172,0.420875421,0.921594521
+173,0.246548323,0.747267423
+174,0.628140704,1.128859804
+175,0.457875458,0.958594558
+176,0.656167979,1.156887079
+177,0.916525663,1.417244763
+178,0,0.5007191
+179,0.265392781,0.766111881
+180,0.59311981,1.09383891
+181,0,0.5007191
+182,0.797448166,1.298167266
+183,0,0.5007191
+184,0,0.5007191
+185,0.544662309,1.045381409
+186,1.151012891,1.651731991
+187,0.617283951,1.118003051
+188,0.73964497,1.24036407
+189,0,0.5007191
+190,0,0.5007191
+191,0.698324022,1.199043122
+192,0.64439633,1.14511543
+193,0.465549348,0.966268448
+194,0.445632799,0.946351899
+195,0.647668394,1.148387494
+196,0.825082508,1.325801608
+197,0.846501129,1.347220229
+198,0.203252033,0.703971133
+199,0.809061489,1.309780589
+200,0.367107195,0.867826295
+201,0,0.5007191
+202,0.304136253,0.804855353
+203,0.714285714,1.215004814
+204,0.781152356,1.281871456
+205,0,0.5007191
+206,0.505050505,1.005769605
+207,0.825082508,1.325801608
+208,0.295508274,0.796227374
+209,0.902266493,1.402985593
+210,0.445632799,0.946351899
+211,0.892325996,1.393045096
+212,0.55187638,1.05259548
+213,0.76298943,1.26370853
+214,0.776397516,1.277116616
+215,1.03493956,1.53565866
+216,0.412541254,0.913260354
+217,0.255623722,0.756342822
+218,0.968992248,1.469711348
+219,0.724637681,1.225356781
+220,0.394944708,0.895663808
+221,0.356125356,0.856844456
+222,0,0.5007191
+223,0.654450262,1.155169362
+224,0.841071188,1.341790288
+225,0.683060109,1.183779209
+226,0.816993464,1.317712564
+227,0.766871166,1.267590266
+228,0.517598344,1.018317444
+229,0.798212005,1.298931105
+230,0,0.5007191
+231,0.313283208,0.814002308
+232,0.839715169,1.340434269
+233,0.517598344,1.018317444
+234,0.825082508,1.325801608
+235,0.559284116,1.060003216
+236,0.429553265,0.930272365
+237,0.438596491,0.939315591
+238,0.382262997,0.882982097
+239,0.947551731,1.448270831
+240,0.232774674,0.733493774
+241,1.130828114,1.631547214
+242,0.356125356,0.856844456
+243,0.344352617,0.845071717
+244,0.748502994,1.249222094
+245,0.753012048,1.253731148
+246,0.816993464,1.317712564
+247,0.796178344,1.296897444
+248,0.843113449,1.343832549
+249,0,0.5007191
+250,1.376376376,1.877095476
+251,0.736160188,1.236879288
+252,0.690607735,1.191326835
+253,1.131221719,1.631940819
+254,0.318066158,0.818785258
+255,0.356125356,0.856844456
+256,0.543951262,1.044670362
+257,0.318066158,0.818785258
+258,0.576302444,1.077021544
+259,1.035196687,1.535915787
+260,0.843113449,1.343832549
+261,0.636132316,1.136851416
+262,0.394321767,0.895040867
+263,0.713121434,1.213840534
+264,0.796178344,1.296897444
+265,0.989119683,1.489838783
+266,0.910746812,1.411465912
+267,0.909090909,1.409810009
+268,1.103752759,1.604471859
+269,0.928505107,1.429224207
+270,0.58685446,1.08757356
+271,0.27593819,0.77665729
+272,0,0.5007191
+273,0.410509031,0.911228131
+274,0.440917108,0.941636208
+275,0.683060109,1.183779209
+276,0.356125356,0.856844456
+277,0,0.5007191
+278,0.493096647,0.993815747
+279,0.776397516,1.277116616
+280,1.243781095,1.744500195
+281,0,0.5007191
+282,0,0.5007191
+283,0.850340136,1.351059236
+284,0.368731563,0.869450663
+285,0.382262997,0.882982097
+286,0.249500998,0.750220098
+287,0.933706816,1.434425916
+288,0.713121434,1.213840534
+289,0.279642058,0.780361158
+290,0.318066158,0.818785258
+291,0,0.5007191
+292,0.252525253,0.753244353
+293,1.204238921,1.704958021
+294,0.457875458,0.958594558
+295,0.322997416,0.823716516
+296,1.638930913,2.139650013
+297,0.262054507,0.762773607
+298,0.299760192,0.800479292
+299,1.134889754,1.635608854
+300,0.712250712,1.212969812
+301,0.505050505,1.005769605
+302,0.891265597,1.391984697
+303,0,0.5007191
+304,0.299760192,0.800479292
+305,1.196888091,1.697607191
+306,1.208490963,1.709210063
+307,0.796178344,1.296897444
+308,0.544662309,1.045381409
+309,0,0.5007191
+310,0.272331155,0.773050255
+311,0.782472613,1.283191713
+312,0.656167979,1.156887079
+313,0.816993464,1.317712564
+314,0.684931507,1.185650607
+315,0.636132316,1.136851416
+316,1.214329083,1.715048183
+317,0.724637681,1.225356781
+318,0.608272506,1.108991606
+319,0.822860563,1.323579663
+320,0,0.5007191
+321,0.766871166,1.267590266
+322,0.265392781,0.766111881
+323,0.344352617,0.845071717
+324,0.886524823,1.387243923
+325,0.797993616,1.298712716
+326,0.954198473,1.454917573
+327,0.283446712,0.784165812
+328,1.006441224,1.507160324
+329,1.272264631,1.772983731
+330,1.523461304,2.024180404
+331,0,0.5007191
+332,0.591016548,1.091735648
+333,0,0.5007191
+334,0,0.5007191
+335,0.582750583,1.083469683
+336,0.455373406,0.956092506
+337,0.566893424,1.067612524
+338,0,0.5007191
+339,1.016260163,1.516979263
+340,1.693766938,2.194486038
+341,1.022494888,1.523213988
+342,0.322997416,0.823716516
+343,0.544662309,1.045381409
+344,0.68119891,1.18191801
+345,0,0.5007191
+346,0.73964497,1.24036407
+347,1.272912424,1.773631524
+348,0.249500998,0.750220098
+349,0,0.5007191
+350,0,0.5007191
+351,1.322751323,1.823470423
+352,0.796178344,1.296897444
+353,0.246548323,0.747267423
+354,0.769569041,1.270288141
+355,0.404530744,0.905249844
+356,1.006441224,1.507160324
+357,1.047414674,1.548133774
+358,0.387596899,0.888315999
+359,1.068376068,1.569095168
+360,1.068376068,1.569095168
+361,0.891265597,1.391984697
+362,0.780640125,1.281359225
+363,0,0.5007191
+364,0.511247444,1.011966544
+365,1.184834123,1.685553223
+366,0.757575758,1.258294858
+367,0.845033801,1.345752901
+368,0.698324022,1.199043122
+369,0.493096647,0.993815747
+370,0.476190476,0.976909576
+371,0.342935528,0.843654628
+372,0.240847784,0.741566884
+373,0.497647485,0.998366585
+374,0.748502994,1.249222094
+375,1.141552511,1.642271611
+376,0,0.5007191
+377,0.944170772,1.444889872
+378,0,0.5007191
+379,0,0.5007191
+380,0.920471281,1.421190381
+381,0.737463127,1.238182227
+382,1.124302932,1.625022032
+383,0.757575758,1.258294858
+384,0.85733882,1.35805792
+385,0,0.5007191
+386,0.414593698,0.915312798
+387,0.76496462,1.26568372
+388,0.978090767,1.478809867
+389,1.769464105,2.270183205
+390,0.984251969,1.484971069
+391,0.476190476,0.976909576
+392,0.283446712,0.784165812
+393,0,0.5007191
+394,0.423011844,0.923730944
+395,1.174536058,1.675255158
+396,0,0.5007191
+397,0.249500998,0.750220098
+398,0.84101214,1.34173124
+399,0.654450262,1.155169362
+400,0.681883434,1.182602534
+401,0,0.5007191
+402,0.329380764,0.830099864
+403,0.859106529,1.359825629
+404,0.252525253,0.753244353
+405,0.596089652,1.096808752
+406,1.361655773,1.862374873
+407,0.729203127,1.229922227
+408,0.318066158,0.818785258
+409,0.530785563,1.031504663
+410,0.574712644,1.075431744
+411,0.287356322,0.788075422
+412,0.68812493,1.18884403
+413,0,0.5007191
+414,0.838926174,1.339645274
+415,0.613286233,1.114005333
+416,0.636132316,1.136851416
+417,0.603864734,1.104583834
+418,0.951886466,1.452605566
+419,0.677506775,1.178225875
+420,0.318066158,0.818785258
+421,1.201550388,1.702269488
+422,1.177024482,1.677743582
+423,0.757575758,1.258294858
+424,0.650026001,1.150745101
+425,0,0.5007191
+426,0.272331155,0.773050255
+427,0.511247444,1.011966544
+428,0.362318841,0.863037941
+429,0.465549348,0.966268448
+430,1.020408163,1.521127263
+431,0.608272506,1.108991606
+432,0.188536953,0.689256053
+433,0.258799172,0.759518272
+434,1.062151008,1.562870108
+435,0.829187396,1.329906496
+436,0.788367204,1.289086304
+437,0.451263538,0.951982638
+438,0.537634409,1.038353509
+439,0.830564784,1.331283884
+440,0.836120401,1.336839501
+441,0.786163522,1.286882622
+442,0,0.5007191
+443,0,0.5007191
+444,0.262054507,0.762773607
+445,0.318066158,0.818785258
+446,0.318066158,0.818785258
+447,1.048218029,1.548937129
+448,0.828363154,1.329082254
+449,0.499001996,0.999721096
+450,0.279642058,0.780361158
+451,0.295508274,0.796227374
+452,0.599520384,1.100239484
+453,0.530785563,1.031504663
+454,0.660300691,1.161019791
+455,0.404530744,0.905249844
+456,0.656167979,1.156887079
+457,0.908490254,1.409209354
+458,0,0.5007191
+459,0.661375661,1.162094761
+460,0,0.5007191
+461,0,0.5007191
+462,0.481695568,0.982414668
+463,0.213675214,0.714394314
+464,0.205254516,0.705973616
+465,0.283446712,0.784165812
+466,1.022494888,1.523213988
+467,1.310272537,1.810991637
+468,0.511247444,1.011966544
+469,0.566893424,1.067612524
+470,0,0.5007191
+471,1.01010101,1.51082011
+472,0.722543353,1.223262453
+473,0,0.5007191
+474,0.963391137,1.464110237
+475,1.084128361,1.584847461
+476,0.457875458,0.958594558
+477,0.304136253,0.804855353
+478,0.436300175,0.937019275
+479,0.438596491,0.939315591
+480,0,0.5007191
+481,0,0.5007191
+482,0,0.5007191
+483,0.899280576,1.399999676
+484,1.126126126,1.626845226
+485,1.070663812,1.571382912
+486,0.283446712,0.784165812
+487,0.544662309,1.045381409
+488,0.27593819,0.77665729
+489,0.524109015,1.024828115
+490,0,0.5007191
+491,0,0.5007191
+492,1.361655773,1.862374873
+493,0.615763547,1.116482647
+494,0.714285714,1.215004814
+495,0.899280576,1.399999676
+496,0.636132316,1.136851416
+497,0.287356322,0.788075422
+498,0.338753388,0.839472488
+499,0.318066158,0.818785258
+500,0.910746812,1.411465912
+501,1.436781609,1.937500709
+502,0,0.5007191
+503,1.177024482,1.677743582
+504,0.752445448,1.253164548
+505,0.404530744,0.905249844
+506,0.872600349,1.373319449
+507,0.862068966,1.362788066
+508,1,1.5007191
+509,0.666666667,1.167385767
+510,1.783398184,2.284117284
+511,0,0.5007191
+512,1.177024482,1.677743582
+513,0.976856026,1.477575126
+514,0,0.5007191
+515,0.688705234,1.189424334
+516,0.517598344,1.018317444
+517,0.544662309,1.045381409
+518,0.96764205,1.46836115
+519,0,0.5007191
+520,0.423011844,0.923730944
+521,0,0.5007191
+522,0.7852077,1.2859268
+523,0.599520384,1.100239484
+524,1.09317188,1.59389098
+525,0.661375661,1.162094761
+526,0.350140056,0.850859156
+527,0.338753388,0.839472488
+528,0.952380952,1.453100052
+529,0.738508803,1.239227903
+530,0.32808399,0.82880309
+531,1.261829653,1.762548753
+532,0.308641975,0.809361075
+533,0.829531315,1.330250415
+534,0.344352617,0.845071717
+535,0.32808399,0.82880309
+536,0.283446712,0.784165812
+537,0.97924011,1.47995921
+538,0.487329435,0.988048535
+539,0.524109015,1.024828115
+540,0,0.5007191
+541,0.215889465,0.716608565
+542,0,0.5007191
+543,0.324254215,0.824973315
+544,0.268817204,0.769536304
+545,1.037037037,1.537756137
+546,0,0.5007191
+547,0.974658869,1.475377969
+548,0.972157412,1.472876512
+549,0.850340136,1.351059236
+550,0.926337632,1.427056732
+551,0.350140056,0.850859156
+552,0.775193798,1.275912898
+553,1.104417671,1.605136771
+554,0.570776256,1.071495356
+555,0.455373406,0.956092506
+556,0.660720185,1.161439285
+557,0.418760469,0.919479569
+558,0.410509031,0.911228131
+559,0.874125874,1.374844974
+560,1.052064983,1.552784083
+561,0.295508274,0.796227374
+562,0.539025442,1.039744542
+563,0.318066158,0.818785258
+564,0.82781457,1.32853367
+565,0.881834215,1.382553315
+566,0.972762646,1.473481746
+567,0,0.5007191
+568,0.199362041,0.700081141
+569,0,0.5007191
+570,0.810635538,1.311354638
+571,0.350140056,0.850859156
+572,0.885296382,1.386015482
+573,0.786163522,1.286882622
+574,0,0.5007191
+575,0,0.5007191
+576,0.27593819,0.77665729
+577,0.394944708,0.895663808
+578,1.398210291,1.898929391
+579,0.333333333,0.834052433
+580,0,0.5007191
+581,0,0.5007191
+582,0,0.5007191
+583,0.608272506,1.108991606
+584,1.090404441,1.591123541
+585,0.899280576,1.399999676
+586,0.902276513,1.402995613
+587,0.574712644,1.075431744
+588,0.838604562,1.339323662
+589,0.925925926,1.426645026
+590,1.212751213,1.713470313
+591,0.899280576,1.399999676
+592,0.322997416,0.823716516
+593,0.481695568,0.982414668
+594,0.886524823,1.387243923
+595,1.322751323,1.823470423
+596,0.724637681,1.225356781
+597,0.362318841,0.863037941
+598,0.880067978,1.380787078
+599,0.308641975,0.809361075
+600,0.596455351,1.097174451
+601,0.268817204,0.769536304
+602,0.319284802,0.820003902
+603,1.048218029,1.548937129
+604,1.025354213,1.526073313
+605,0.82781457,1.32853367
+606,0.517598344,1.018317444
+607,0.732600733,1.233319833
+608,1.204238921,1.704958021
+609,1.427212179,1.927931279
+610,0.225225225,0.725944325
+611,0,0.5007191
+612,0,0.5007191
+613,0.279642058,0.780361158
+614,0.539125077,1.039844177
+615,0.481695568,0.982414668
+616,0.407166124,0.907885224
+617,0.246548323,0.747267423
+618,0.896057348,1.396776448
+619,0.262054507,0.762773607
+620,1.065643649,1.566362749
+621,0,0.5007191
+622,0.283446712,0.784165812
+623,0,0.5007191
+624,1.177856302,1.678575402
+625,0.690607735,1.191326835
+626,1.00040016,1.50111926
+627,0.322997416,0.823716516
+628,1.060820368,1.561539468
+629,0.920810313,1.421529413
+630,0.883108542,1.383827642
+631,0.207296849,0.708015949
+632,0,0.5007191
+633,0.333333333,0.834052433
+634,1.454016721,1.954735821
+635,0.721500722,1.222219822
+636,0.993009215,1.493728315
+637,0,0.5007191
+638,1.13999088,1.64070998
+639,0.920810313,1.421529413
+640,0.778816199,1.279535299
+641,1.184834123,1.685553223
+642,0.816033425,1.316752525
+643,1.559714795,2.060433895
+644,0.946539452,1.447258552
+645,0.748502994,1.249222094
+646,0.792443261,1.293162361
+647,0.617283951,1.118003051
+648,1.153846154,1.654565254
+649,1.151012891,1.651731991
+650,1.492942454,1.993661554
+651,0.854700855,1.355419955
+652,0.985027581,1.485746681
+653,0.295508274,0.796227374
+654,0.944218478,1.444937578
+655,0,0.5007191
+656,0.577901063,1.078620163
+657,0.776397516,1.277116616
+658,0.78369906,1.28441816
+659,0.465549348,0.966268448
+660,0.944822373,1.445541473
+661,0.505050505,1.005769605
+662,0.698870625,1.199589725
+663,0.382262997,0.882982097
+664,0.220458554,0.721177654
+665,0,0.5007191
+666,0.377643505,0.878362605
+667,0,0.5007191
+668,0.265392781,0.766111881
+669,0.73176443,1.23248353
+670,1.593806922,2.094526022
+671,0.27593819,0.77665729
+672,0.954198473,1.454917573
+673,0.222816399,0.723535499
+674,0.249500998,0.750220098
+675,0.438596491,0.939315591
+676,0.255623722,0.756342822
+677,0.39184953,0.89256863
+678,0,0.5007191
+679,0.636132316,1.136851416
+680,0.805931657,1.306650757
+681,0.287356322,0.788075422
+682,0.606131707,1.106850807
+683,0,0.5007191
+684,0.95959596,1.46031506
+685,0.566893424,1.067612524
+686,1.338688086,1.839407186
+687,0.544662309,1.045381409
+688,0.666666667,1.167385767
+689,0.333333333,0.834052433
+690,0,0.5007191
+691,1.00922722,1.50994632
+692,0.945626478,1.446345578
+693,0.360750361,0.861469461
+694,0.588235294,1.088954394
+695,0.314465409,0.815184509
+696,0.750750751,1.251469851
+697,0.750750751,1.251469851
+698,0.628140704,1.128859804
+699,0.457875458,0.958594558
+700,0.774473358,1.275192458
+701,0.291375291,0.792094391
+702,1.515151515,2.015870615
+703,1.497005988,1.997725088
+704,0.258799172,0.759518272
+705,0.932140194,1.432859294
+706,0.858000858,1.358719958
+707,0,0.5007191
+708,0.716907548,1.217626648
+709,1.310272537,1.810991637
+710,1.307320998,1.808040098
+711,1.01010101,1.51082011
+712,1.075268817,1.575987917
+713,0,0.5007191
+714,0.481695568,0.982414668
+715,0,0.5007191
+716,0.177304965,0.678024065
+717,0,0.5007191
+718,0.603864734,1.104583834
+719,0.412541254,0.913260354
+720,0,0.5007191
+721,0.530785563,1.031504663
+722,0,0.5007191
+723,0.621890547,1.122609647
+724,0.982431808,1.483150908
+725,0.766871166,1.267590266
+726,1.182033097,1.682752197
+727,0,0.5007191
+728,0.291375291,0.792094391
+729,0.790754258,1.291473358
+730,0.730994152,1.231713252
+731,0.249500998,0.750220098
+732,0.464252553,0.964971653
+733,0,0.5007191
+734,0.313283208,0.814002308
+735,0.997719498,1.498438598
+736,0,0.5007191
+737,0.537634409,1.038353509
+738,1.220362622,1.721081722
+739,0.636132316,1.136851416
+740,0.252525253,0.753244353
+741,0.786163522,1.286882622
+742,0,0.5007191
+743,0.806451613,1.307170713
+744,1.243182547,1.743901647
+745,0.809061489,1.309780589
+746,0.566893424,1.067612524
+747,0.94055681,1.44127591
+748,0,0.5007191
+749,0.566893424,1.067612524
+750,0.821018062,1.321737162
+751,0.706214689,1.206933789
+752,1,1.5007191
+753,0.926337632,1.427056732
+754,0.598086124,1.098805224
+755,0.986193294,1.486912394
+756,1.088677751,1.589396851
+757,1.091703057,1.592422157
+758,0.445632799,0.946351899
+759,0.279642058,0.780361158
+760,0.787474523,1.288193623
+761,0.283446712,0.784165812
+762,0.801590355,1.302309455
+763,1.068376068,1.569095168
+764,0.222816399,0.723535499
+765,0.722125939,1.222845039
+766,0,0.5007191
+767,0.806451613,1.307170713
+768,0,0.5007191
+769,0,0.5007191
+770,0,0.5007191
+771,1.728110599,2.228829699
+772,0.382262997,0.882982097
+773,0,0.5007191
+774,0.73964497,1.24036407
+775,0,0.5007191
+776,0.287356322,0.788075422
+777,1.272264631,1.772983731
+778,0,0.5007191
+779,0.238095238,0.738814338
+780,0.896659942,1.397379042
+781,0.404530744,0.905249844
+782,0.570776256,1.071495356
+783,0.67662661,1.17734571
+784,0.375375375,0.876094475
+785,0.748502994,1.249222094
+786,0.507264021,1.007983121
+787,0.912408759,1.413127859
+788,0.881834215,1.382553315
+789,0.268817204,0.769536304
+790,1.221498371,1.722217471
+791,0,0.5007191
+792,1.004984724,1.505703824
+793,0,0.5007191
+794,0.464370145,0.965089245
+795,0.608272506,1.108991606
+796,0.883256528,1.383975628
+797,0.559284116,1.060003216
+798,0.95129376,1.45201286
+799,0,0.5007191
+800,0,0.5007191
+801,0.73313783,1.23385693
+802,0.891265597,1.391984697
+803,0.965847628,1.466566728
+804,0.599520384,1.100239484
+805,1.354096141,1.854815241
+806,0.511247444,1.011966544
+807,0.770609319,1.271328419
+808,0.272331155,0.773050255
+809,1.241254796,1.741973896
+810,1.253132832,1.753851932
+811,0.80348944,1.30420854
+812,0.628140704,1.128859804
+813,0.634582191,1.135301291
+814,0.706214689,1.206933789
+815,0.537634409,1.038353509
+816,0.722983257,1.223702357
+817,0.635013677,1.135732777
+818,0.592417062,1.093136162
+819,0.249500998,0.750220098
+820,0.357653791,0.858372891
+821,0.589678272,1.090397372
+822,0.996810207,1.497529307
+823,1.360039565,1.860758665
+824,0.560538117,1.061257217
+825,0.465549348,0.966268448
+826,0,0.5007191
+827,0.925925926,1.426645026
+828,0.626566416,1.127285516
+829,0.45045045,0.95116955
+830,0,0.5007191
+831,0.730994152,1.231713252
+832,0.787649653,1.288368753
+833,0.866414619,1.367133719
+834,0.436300175,0.937019275
+835,0.769041467,1.269760567
+836,0.757575758,1.258294858
+837,1.234567901,1.735287001
+838,1.016260163,1.516979263
+839,0.246548323,0.747267423
+840,1.271693597,1.772412697
+841,1.269956459,1.770675559
+842,0.899280576,1.399999676
+843,0,0.5007191
+844,1.016260163,1.516979263
+845,1.052720229,1.553439329
+846,0,0.5007191
+847,0.790424571,1.291143671
+848,0,0.5007191
+849,0.272331155,0.773050255
+850,0.9887676,1.4894867
+851,0.766871166,1.267590266
+852,0.504561234,1.005280334
+853,0.299760192,0.800479292
+854,1.170589724,1.671308824
+855,0.838926174,1.339645274
+856,0.688705234,1.189424334
+857,0.32808399,0.82880309
+858,0.279642058,0.780361158
+859,1.25600699,1.75672609
+860,0.581395349,1.082114449
+861,0.443923574,0.944642674
+862,0.524109015,1.024828115
+863,0.780640125,1.281359225
+864,0.291375291,0.792094391
+865,0.649215747,1.149934847
+866,0.299760192,0.800479292
+867,0.875718089,1.376437189
+868,0,0.5007191
+869,0.974658869,1.475377969
+870,1.724137931,2.224857031
+871,0.505050505,1.005769605
+872,0.69421304,1.19493214
+873,0.476190476,0.976909576
+874,1.212650369,1.713369469
+875,0.350140056,0.850859156
+876,0.925191647,1.425910747
+877,0,0.5007191
+878,0.588235294,1.088954394
+879,0.92936803,1.43008713
+880,0.517598344,1.018317444
+881,1.008690255,1.509409355
+882,1.337613697,1.838332797
+883,0.493096647,0.993815747
+884,0.709219858,1.209938958
+885,0,0.5007191
+886,0.900900901,1.401620001
+887,0.802093887,1.302812987
+888,0.429553265,0.930272365
+889,0.279642058,0.780361158
+890,1.022494888,1.523213988
+891,0.696767001,1.197486101
+892,0.235404896,0.736123996
+893,0.579374276,1.080093376
+894,0,0.5007191
+895,0.574712644,1.075431744
+896,1.147666412,1.648385512
+897,0.978090767,1.478809867
+898,0.299760192,0.800479292
+899,0.418760469,0.919479569
+900,0,0.5007191
+901,0.544662309,1.045381409
+902,0.780274657,1.280993757
+903,0.356125356,0.856844456
+904,0.789889415,1.290608515
+905,0.677139762,1.177858862
+906,0.615763547,1.116482647
+907,0.299760192,0.800479292
+908,0.333333333,0.834052433
+909,0.291375291,0.792094391
+910,0.95712098,1.45784008
+911,0.205254516,0.705973616
+912,0.418760469,0.919479569
+913,1.129177958,1.629897058
+914,0.515995872,1.016714972
+915,0.615763547,1.116482647
+916,0.621890547,1.122609647
+917,0.524109015,1.024828115
+918,0.805152979,1.305872079
+919,0,0.5007191
+920,0.481695568,0.982414668
+921,1.097178683,1.597897783
+922,0.499001996,0.999721096
+923,1.232741617,1.733460717
+924,1.232741617,1.733460717
+925,0.757575758,1.258294858
+926,0,0.5007191
+927,0,0.5007191
+928,1.035196687,1.535915787
+929,0,0.5007191
+930,0,0.5007191
+931,0.279642058,0.780361158
+932,0.695566326,1.196285426
+933,0.318066158,0.818785258
+934,0.574712644,1.075431744
+935,0.268817204,0.769536304
+936,0.825082508,1.325801608
+937,0.3894081,0.8901272
+938,0.55187638,1.05259548
+939,0.737286785,1.238005885
+940,0.517598344,1.018317444
+941,0.936329588,1.437048688
+942,0.757575758,1.258294858
+943,1.610936956,2.111656056
+944,0.968992248,1.469711348
+945,0.268817204,0.769536304
+946,1.039152588,1.539871688
+947,0,0.5007191
+948,0.322997416,0.823716516
+949,0.862068966,1.362788066
+950,1.122658455,1.623377555
+951,0.391236307,0.891955407
+952,0.838926174,1.339645274
+953,0.318066158,0.818785258
+954,0.628140704,1.128859804
+955,0.318066158,0.818785258
+956,0.933005644,1.433724744
+957,0,0.5007191
+958,0.938967136,1.439686236
+959,0.505050505,1.005769605
+960,0.812819322,1.313538422
+961,0.230202578,0.730921678
+962,0.374027528,0.874746628
+963,0.559284116,1.060003216
+964,0.978890024,1.479609124
+965,0.574712644,1.075431744
+966,0.755909841,1.256628941
+967,0.262054507,0.762773607
+968,0.906555091,1.407274191
+969,0.862068966,1.362788066
+970,1.074436995,1.575156095
+971,0,0.5007191
+972,0.872817955,1.373537055
+973,0.382262997,0.882982097
+974,0.779376499,1.280095599
+975,0.235404896,0.736123996
+976,0.94390507,1.44462417
+977,0.806451613,1.307170713
+978,0.313283208,0.814002308
+979,0.333333333,0.834052433
+980,0.394944708,0.895663808
+981,0,0.5007191
+982,0,0.5007191
+983,0.715922108,1.216641208
+984,1.472320377,1.973039477
+985,0.82781457,1.32853367
+986,1.406926407,1.907645507
+987,0.27593819,0.77665729
+988,0.601926164,1.102645264
+989,0.544662309,1.045381409
+990,0.530785563,1.031504663
+991,0,0.5007191
+992,0.308641975,0.809361075
+993,0.283446712,0.784165812
+994,0.295508274,0.796227374
+995,0.368731563,0.869450663
+996,0,0.5007191
+997,0.55187638,1.05259548
+998,0.249500998,0.750220098
+999,0.617283951,1.118003051
+1000,0.611127408,1.111846508

A2_Q10_Google_Colab_Seq2seq_based_translator_Analysis.ipynb

@@ -0,0 +1,592 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "8NIm_0b_sjJc",
+    "outputId": "615bda96-593f-4851-b6e6-6acb84376b93"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: sacrebleu in /usr/local/lib/python3.10/dist-packages (2.4.3)\n",
+      "Requirement already satisfied: portalocker in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (2.10.1)\n",
+      "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (2024.9.11)\n",
+      "Requirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (0.9.0)\n",
+      "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (1.26.4)\n",
+      "Requirement already satisfied: colorama in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (0.4.6)\n",
+      "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (5.3.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install sacrebleu\n",
+    "\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torch.utils.data import DataLoader, Dataset\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import sacrebleu\n",
+    "import json\n",
+    "import csv\n",
+    "from collections import Counter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "XAapN08evSpV",
+    "outputId": "61281ff6-7979-48a5-9da9-a92d17f17210"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "EN to IC\n",
+      "<s>\n",
+      "<en> give three tips for staying healthy </en>\n",
+      "<ic> gefðu þrjú ráð til að halda heilsu </ic>\n",
+      "</s>\n",
+      "IC to EN\n",
+      "<s>\n",
+      "<ic> gefðu þrjú ráð til að halda heilsu </ic>\n",
+      "<en> give three tips for staying healthy </en>\n",
+      "</s>\n",
+      "\n",
+      "EN to IC\n",
+      "<s>\n",
+      "<en> 1 eat a balanced and nutritious diet make sure your meals are inclusive of a variety of fruits and vegetables lean protein whole grains and healthy fats this helps to provide your body with the essential nutrients to function at its best and can help prevent chronic diseases 2 engage in regular physical activity exercise is crucial for maintaining strong bones muscles and cardiovascular health aim for at least 150 minutes of moderate aerobic exercise or 75 minutes of vigorous exercise each week 3 get enough sleep getting enough quality sleep is crucial for physical and mental wellbeing it helps to regulate mood improve cognitive function and supports healthy growth and immune function aim for 79 hours of sleep each night </en>\n",
+      "<ic> 1 borðaðu hollt og næringarríkt mataræði gakktu úr skugga um að máltíðirnar þínar innihaldi margs konar ávexti og grænmeti magurt prótein heilkorn og holla fitu þetta hjálpar til við að veita líkamanum nauðsynleg næringarefni til að virka sem best og getur hjálpað til við að koma í veg fyrir langvinna sjúkdóma 2 taktu þátt í reglulegri hreyfingu hreyfing er mikilvæg til að viðhalda sterkum beinum vöðvum og hjarta og æðaheilbrigði miðaðu við að minnsta kosti 150 mínútur af hóflegri þolþjálfun eða 75 mínútur af öflugri hreyfingu í hverri viku 3 fáðu nægan svefn að fá nægan gæðasvefn skiptir sköpum fyrir líkamlega og andlega vellíðan það hjálpar til við að stjórna skapi bæta vitræna virkni og styðja við heilbrigðan vöxt og ónæmisvirkni miðaðu við 79 tíma svefn á hverri nóttu </ic>\n",
+      "</s>\n",
+      "IC to EN\n",
+      "<s>\n",
+      "<ic> 1 borðaðu hollt og næringarríkt mataræði gakktu úr skugga um að máltíðirnar þínar innihaldi margs konar ávexti og grænmeti magurt prótein heilkorn og holla fitu þetta hjálpar til við að veita líkamanum nauðsynleg næringarefni til að virka sem best og getur hjálpað til við að koma í veg fyrir langvinna sjúkdóma 2 taktu þátt í reglulegri hreyfingu hreyfing er mikilvæg til að viðhalda sterkum beinum vöðvum og hjarta og æðaheilbrigði miðaðu við að minnsta kosti 150 mínútur af hóflegri þolþjálfun eða 75 mínútur af öflugri hreyfingu í hverri viku 3 fáðu nægan svefn að fá nægan gæðasvefn skiptir sköpum fyrir líkamlega og andlega vellíðan það hjálpar til við að stjórna skapi bæta vitræna virkni og styðja við heilbrigðan vöxt og ónæmisvirkni miðaðu við 79 tíma svefn á hverri nóttu </ic>\n",
+      "<en> 1 eat a balanced and nutritious diet make sure your meals are inclusive of a variety of fruits and vegetables lean protein whole grains and healthy fats this helps to provide your body with the essential nutrients to function at its best and can help prevent chronic diseases 2 engage in regular physical activity exercise is crucial for maintaining strong bones muscles and cardiovascular health aim for at least 150 minutes of moderate aerobic exercise or 75 minutes of vigorous exercise each week 3 get enough sleep getting enough quality sleep is crucial for physical and mental wellbeing it helps to regulate mood improve cognitive function and supports healthy growth and immune function aim for 79 hours of sleep each night </en>\n",
+      "</s>\n",
+      "\n",
+      "EN to IC\n",
+      "<s>\n",
+      "<en> what are the three primary colors </en>\n",
+      "<ic> hverjir eru þrír aðallitirnir </ic>\n",
+      "</s>\n",
+      "IC to EN\n",
+      "<s>\n",
+      "<ic> hverjir eru þrír aðallitirnir </ic>\n",
+      "<en> what are the three primary colors </en>\n",
+      "</s>\n",
+      "\n",
+      "EN to IC\n",
+      "<s>\n",
+      "<en> the three primary colors are red blue and yellow these colors are called primary because they cannot be created by mixing other colors and all other colors can be made by combining them in various proportions in the additive color system used for light the primary colors are red green and blue rgb </en>\n",
+      "<ic> aðallitirnir þrír eru rauður blár og gulur þessir litir eru kallaðir frumefni vegna þess að ekki er hægt að búa þá til með því að blanda öðrum litum og alla aðra liti er hægt að búa til með því að sameina þá í ýmsum hlutföllum í auklitakerfinu notað fyrir ljós eru aðallitirnir rauður grænn og blár rgb </ic>\n",
+      "</s>\n",
+      "IC to EN\n",
+      "<s>\n",
+      "<ic> aðallitirnir þrír eru rauður blár og gulur þessir litir eru kallaðir frumefni vegna þess að ekki er hægt að búa þá til með því að blanda öðrum litum og alla aðra liti er hægt að búa til með því að sameina þá í ýmsum hlutföllum í auklitakerfinu notað fyrir ljós eru aðallitirnir rauður grænn og blár rgb </ic>\n",
+      "<en> the three primary colors are red blue and yellow these colors are called primary because they cannot be created by mixing other colors and all other colors can be made by combining them in various proportions in the additive color system used for light the primary colors are red green and blue rgb </en>\n",
+      "</s>\n",
+      "\n",
+      "EN to IC\n",
+      "<s>\n",
+      "<en> describe the structure of an atom </en>\n",
+      "<ic> lýstu byggingu atóms </ic>\n",
+      "</s>\n",
+      "IC to EN\n",
+      "<s>\n",
+      "<ic> lýstu byggingu atóms </ic>\n",
+      "<en> describe the structure of an atom </en>\n",
+      "</s>\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "\n",
+    "\n",
+    "# Load the Icelandic_cleaned.json dataset\n",
+    "with open('/content/Icelandic_cleaned.json', 'r', encoding='utf-8') as f:\n",
+    "    data = json.load(f)\n",
+    "\n",
+    "# Extract the first 1,000 English and Icelandic sentences for BLEU and CHRF calculation\n",
+    "en_sentences = [entry['input'] for entry in data[:1000]]\n",
+    "ic_sentences = [entry['output'] for entry in data[:1000]]\n",
+    "\n",
+    "# Tokenizer and Vectorization\n",
+    "tokenizer = lambda x: x.split()\n",
+    "\n",
+    "def build_vocab(sentences):\n",
+    "    counter = Counter()\n",
+    "    for sentence in sentences:\n",
+    "        counter.update(tokenizer(sentence))\n",
+    "    return counter\n",
+    "\n",
+    "en_vocab = build_vocab(en_sentences)\n",
+    "ic_vocab = build_vocab(ic_sentences)\n",
+    "\n",
+    "# Adding special tokens\n",
+    "en_vocab = {'<s>': 1, '</s>': 2, '<pad>': 0, '<unk>': 3, **en_vocab}\n",
+    "ic_vocab = {'<s>': 1, '</s>': 2, '<pad>': 0, '<unk>': 3, **ic_vocab}\n",
+    "\n",
+    "def sentence_to_tensor(sentence, vocab, max_len=MAX_LEN):\n",
+    "    tokens = tokenizer(sentence)\n",
+    "    indices = [vocab.get(token, vocab['<unk>']) for token in tokens]\n",
+    "    indices = [vocab['<s>']] + indices + [vocab['</s>']]\n",
+    "    if len(indices) < max_len:\n",
+    "        indices += [vocab['<pad>']] * (max_len - len(indices))\n",
+    "    else:\n",
+    "        indices = indices[:max_len]\n",
+    "    return torch.tensor(indices)\n",
+    "\n",
+    "\n",
+    "VOCAB_SIZE = 10000\n",
+    "EMBEDDING_DIM = 256\n",
+    "HIDDEN_DIM = 512\n",
+    "BATCH_SIZE = 32\n",
+    "NUM_EPOCHS = 10\n",
+    "MAX_LEN = 50\n",
+    "\n",
+    "# Prepare dataset and dataloaders\n",
+    "en_tensor_sentences = [sentence_to_tensor(s, en_vocab) for s in en_sentences]\n",
+    "ic_tensor_sentences = [sentence_to_tensor(s, ic_vocab) for s in ic_sentences]\n",
+    "\n",
+    "# Split data into training and validation sets (80% train, 20% validation)\n",
+    "train_size = int(0.8 * len(en_tensor_sentences))\n",
+    "train_en, val_en = en_tensor_sentences[:train_size], en_tensor_sentences[train_size:]\n",
+    "train_ic, val_ic = ic_tensor_sentences[:train_size], ic_tensor_sentences[train_size:]\n",
+    "\n",
+    "# Sample Data Printing in Specified Format\n",
+    "def print_sample_data(en_sentences, ic_sentences):\n",
+    "    for i in range(5):\n",
+    "        en_sample = en_sentences[i]\n",
+    "        ic_sample = ic_sentences[i]\n",
+    "\n",
+    "        print(\"EN to IC\")\n",
+    "        print(\"<s>\")\n",
+    "        print(f\"<en> {en_sample} </en>\")\n",
+    "        print(f\"<ic> {ic_sample} </ic>\")\n",
+    "        print(\"</s>\")\n",
+    "\n",
+    "        print(\"IC to EN\")\n",
+    "        print(\"<s>\")\n",
+    "        print(f\"<ic> {ic_sample} </ic>\")\n",
+    "        print(f\"<en> {en_sample} </en>\")\n",
+    "        print(\"</s>\")\n",
+    "        print()\n",
+    "\n",
+    "print_sample_data(en_sentences, ic_sentences)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "id": "nzbNHJI1vSlg"
+   },
+   "outputs": [],
+   "source": [
+    "# Custom Dataset\n",
+    "class TranslationDataset(Dataset):\n",
+    "    def __init__(self, en_sentences, ic_sentences):\n",
+    "        self.en_sentences = en_sentences\n",
+    "        self.ic_sentences = ic_sentences\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return len(self.en_sentences)\n",
+    "\n",
+    "    def __getitem__(self, idx):\n",
+    "        return self.en_sentences[idx], self.ic_sentences[idx]\n",
+    "\n",
+    "# Prepare dataloader\n",
+    "train_dataset = TranslationDataset(train_en, train_ic)\n",
+    "val_dataset = TranslationDataset(val_en, val_ic)\n",
+    "\n",
+    "# Define a collate_fn to pad sequences dynamically\n",
+    "def collate_fn(batch):\n",
+    "    en_batch, ic_batch = zip(*batch)\n",
+    "    en_batch = torch.stack(en_batch, dim=0)\n",
+    "    ic_batch = torch.stack(ic_batch, dim=0)\n",
+    "    return en_batch, ic_batch\n",
+    "\n",
+    "train_dataloader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_fn)\n",
+    "val_dataloader = DataLoader(val_dataset, batch_size=BATCH_SIZE, shuffle=False, collate_fn=collate_fn)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "3tVw3ao4vSiX"
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "# Seq2Seq Model\n",
+    "class Seq2SeqModel(nn.Module):\n",
+    "    def __init__(self, input_dim, output_dim, embedding_dim, hidden_dim, num_layers=1):\n",
+    "        super(Seq2SeqModel, self).__init__()\n",
+    "\n",
+    "        self.encoder_embedding = nn.Embedding(input_dim, embedding_dim)\n",
+    "        self.encoder_lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers, batch_first=True)\n",
+    "\n",
+    "        self.decoder_embedding = nn.Embedding(output_dim, embedding_dim)\n",
+    "        self.decoder_lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers, batch_first=True)\n",
+    "        self.fc_out = nn.Linear(hidden_dim, output_dim)\n",
+    "\n",
+    "    def forward(self, src, trg):\n",
+    "        embedded_src = self.encoder_embedding(src)\n",
+    "        encoder_output, (hidden, cell) = self.encoder_lstm(embedded_src)\n",
+    "\n",
+    "        embedded_trg = self.decoder_embedding(trg)\n",
+    "        decoder_output, _ = self.decoder_lstm(embedded_trg, (hidden, cell))\n",
+    "\n",
+    "        output = self.fc_out(decoder_output)\n",
+    "        return output\n",
+    "\n",
+    "# Initialize the Seq2Seq model\n",
+    "model = Seq2SeqModel(len(en_vocab), len(ic_vocab), EMBEDDING_DIM, HIDDEN_DIM, num_layers=1).to(DEVICE)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "caqExHCzvSgZ",
+    "outputId": "e03cd84e-4e07-4cae-f804-406b98cfa0dd"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10, Training Loss: 4.162079634666443, Validation Loss: 1.783459918839591\n",
+      "Epoch 2/10, Training Loss: 1.0344110178947448, Validation Loss: 0.4918278966631208\n",
+      "Epoch 3/10, Training Loss: 0.2632215261459351, Validation Loss: 0.12271245462553841\n",
+      "Epoch 4/10, Training Loss: 0.07123038023710251, Validation Loss: 0.04314851335116795\n",
+      "Epoch 5/10, Training Loss: 0.030836958587169647, Validation Loss: 0.02404651258672987\n",
+      "Epoch 6/10, Training Loss: 0.01885295122861862, Validation Loss: 0.01633326443178313\n",
+      "Epoch 7/10, Training Loss: 0.013474887125194073, Validation Loss: 0.012323189526796341\n",
+      "Epoch 8/10, Training Loss: 0.010358258336782455, Validation Loss: 0.009776035456785135\n",
+      "Epoch 9/10, Training Loss: 0.00829771364107728, Validation Loss: 0.008006346212433917\n",
+      "Epoch 10/10, Training Loss: 0.006895635910332203, Validation Loss: 0.006732985709926912\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Define the loss function and optimizer\n",
+    "criterion = nn.CrossEntropyLoss(ignore_index=ic_vocab['<pad>'])\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
+    "\n",
+    "# Function to train the model\n",
+    "def train_model(model, train_dataloader, val_dataloader, optimizer, criterion, num_epochs=10):\n",
+    "    model.to(DEVICE)\n",
+    "    train_losses, val_losses = [], []\n",
+    "\n",
+    "    for epoch in range(num_epochs):\n",
+    "        model.train()\n",
+    "        epoch_train_loss = 0\n",
+    "        for en_batch, ic_batch in train_dataloader:\n",
+    "            en_batch, ic_batch = en_batch.to(DEVICE), ic_batch.to(DEVICE)\n",
+    "            ic_batch = ic_batch.long()\n",
+    "\n",
+    "            optimizer.zero_grad()\n",
+    "            output = model(en_batch, ic_batch)\n",
+    "\n",
+    "            output_dim = output.shape[-1]\n",
+    "            output = output.reshape(-1, output_dim)\n",
+    "            ic_batch = ic_batch.reshape(-1)\n",
+    "            loss = criterion(output, ic_batch)\n",
+    "\n",
+    "            loss.backward()\n",
+    "            optimizer.step()\n",
+    "\n",
+    "            epoch_train_loss += loss.item()\n",
+    "\n",
+    "        train_losses.append(epoch_train_loss / len(train_dataloader))\n",
+    "\n",
+    "        model.eval()\n",
+    "        epoch_val_loss = 0\n",
+    "        with torch.no_grad():\n",
+    "            for en_batch, ic_batch in val_dataloader:\n",
+    "                en_batch, ic_batch = en_batch.to(DEVICE), ic_batch.to(DEVICE)\n",
+    "                ic_batch = ic_batch.long()\n",
+    "\n",
+    "                output = model(en_batch, ic_batch)\n",
+    "                output_dim = output.shape[-1]\n",
+    "                output = output.reshape(-1, output_dim)\n",
+    "                ic_batch = ic_batch.reshape(-1)\n",
+    "\n",
+    "                loss = criterion(output, ic_batch)\n",
+    "                epoch_val_loss += loss.item()\n",
+    "\n",
+    "        val_losses.append(epoch_val_loss / len(val_dataloader))\n",
+    "\n",
+    "        print(f'Epoch {epoch+1}/{num_epochs}, Training Loss: {train_losses[-1]}, Validation Loss: {val_losses[-1]}')\n",
+    "\n",
+    "    return train_losses, val_losses\n",
+    "\n",
+    "train_losses, val_losses = train_model(model, train_dataloader, val_dataloader, optimizer, criterion, num_epochs=NUM_EPOCHS)\n",
+    "\n",
+    "# Save the trained model\n",
+    "torch.save(model.state_dict(), 'seq2seq_translation_model.pth')\n",
+    "\n",
+    "\n",
+    "def translate_new_sentence(model, sentence, src_vocab, tgt_vocab, max_len=MAX_LEN):\n",
+    "    # Prepare input tensor for the source sentence (English)\n",
+    "    model.eval()  # Set model to evaluation mode\n",
+    "    en_indices = [src_vocab.get(word, src_vocab['<unk>']) for word in sentence.split()]  # Handle unknown words\n",
+    "    en_tensor = torch.tensor(en_indices).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    # Initialize target sentence for translation (Croatian) with start token\n",
+    "    tgt_tensor = torch.tensor([tgt_vocab['<s>']]).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    translated_sentence = []\n",
+    "\n",
+    "    for _ in range(max_len):\n",
+    "        with torch.no_grad():\n",
+    "            output = model(en_tensor, tgt_tensor)\n",
+    "\n",
+    "        # Get the last output token's prediction (the next word)\n",
+    "        output_token = output.argmax(dim=-1)[:, -1]\n",
+    "\n",
+    "        # Get the predicted word from the target vocabulary\n",
+    "        output_token_item = output_token.item()\n",
+    "\n",
+    "        # Check if the token is within the target vocabulary range\n",
+    "        if output_token_item not in tgt_vocab.values():\n",
+    "            translated_word = '<unk>'  # Map to <unk> if not found\n",
+    "        else:\n",
+    "            translated_word = list(tgt_vocab.keys())[list(tgt_vocab.values()).index(output_token_item)]\n",
+    "\n",
+    "        # Append predicted word to the translated sentence\n",
+    "        translated_sentence.append(translated_word)\n",
+    "\n",
+    "        # If we encounter an end token, stop the translation\n",
+    "        if translated_word == '</s>':\n",
+    "            break\n",
+    "\n",
+    "        # Update tgt_tensor for next prediction\n",
+    "        tgt_tensor = torch.cat((tgt_tensor, output_token.unsqueeze(0)), dim=-1)\n",
+    "\n",
+    "    return ' '.join(translated_sentence)\n",
+    "\n",
+    "# BLEU and CHRF Scores Calculation\n",
+    "def calculate_bleu_chrf(en_sentences, ic_sentences, model, en_vocab, ic_vocab, max_len=MAX_LEN):\n",
+    "    bleu_scores = []\n",
+    "    chrf_scores = []\n",
+    "\n",
+    "    for en_sentence, ic_sentence in zip(en_sentences, ic_sentences):\n",
+    "        translated_sentence = translate_new_sentence(model, en_sentence, en_vocab, ic_vocab, max_len)\n",
+    "\n",
+    "        bleu_score = sacrebleu.corpus_bleu([translated_sentence], [[ic_sentence]]).score\n",
+    "        bleu_scores.append(bleu_score)\n",
+    "\n",
+    "        chrf_score = sacrebleu.corpus_chrf([translated_sentence], [[ic_sentence]]).score\n",
+    "        chrf_scores.append(chrf_score)\n",
+    "\n",
+    "    return bleu_scores, chrf_scores\n",
+    "\n",
+    "lstm_bleu_scores, lstm_chrf_scores = calculate_bleu_chrf(en_sentences, ic_sentences, model, en_vocab, ic_vocab)\n",
+    "\n",
+    "# Save BLEU and CHRF scores to CSV\n",
+    "with open('Seq2Seq_BLEU_CHRF_scores.csv', mode='w', newline='', encoding='utf-8') as file:\n",
+    "    writer = csv.writer(file)\n",
+    "    writer.writerow([\"BLEU Score\", \"CHRF Score\"])\n",
+    "    for bleu, chrf in zip(lstm_bleu_scores, lstm_chrf_scores):\n",
+    "        writer.writerow([bleu, chrf])\n",
+    "\n",
+    "\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 487
+    },
+    "id": "pllSNt5vK-AX",
+    "outputId": "ba288b64-8026-4194-94fb-83cf9a54f7c2"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x500 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "\n",
+    "\n",
+    "# Plot the training and validation loss\n",
+    "def plot_losses(train_losses, val_losses):\n",
+    "    plt.figure(figsize=(10, 5))\n",
+    "    plt.plot(train_losses, label='Training Loss')\n",
+    "    plt.plot(val_losses, label='Validation Loss')\n",
+    "    plt.xlabel('Epochs')\n",
+    "    plt.ylabel('Loss')\n",
+    "    plt.legend()\n",
+    "    plt.title('Training and Validation Loss for seq2seq')\n",
+    "    plt.show()\n",
+    "\n",
+    "plot_losses(train_losses, val_losses)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "w4FDUt1Vshjm",
+    "outputId": "540d70b3-62f1-44f5-fab0-0c5cb9285578"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original: This is a test sentence.\n",
+      "Translated: <s> gefðu þrjú ráð halda heilsu borðaðu hollt næringarríkt mataræði gakktu máltíðirnar þínar innihaldi margs konar ávexti grænmeti magurt prótein heilkorn holla fitu þetta veita líkamanum nauðsynleg næringarefni virka best hjálpað koma veg langvinna sjúkdóma taktu þátt reglulegri hreyfing mikilvæg viðhalda sterkum beinum vöðvum hjarta æðaheilbrigði minnsta kosti 150 hóflegri þolþjálfun 75 öflugri viku fáðu fá gæðasvefn skiptir sköpum andlega vellíðan stjórna skapi bæta vitræna virkni heilbrigðan vöxt ónæmisvirkni 79 nóttu hverjir gulur þessir litir kallaðir blanda öðrum litum alla aðra liti sameina ýmsum hlutföllum auklitakerfinu notað ljós grænn rgb byggingu atóm grunnbygging alls efnis samsett þremur tegundum agna rafeindum lýsa má uppbyggingu miðjunni umkringdur rafeindaskýi kjarni gerður róteindir jákvætt nifteindir hlutlausar án hleðslu báðar þessar staðsettar miðju inniheldur mestan hluta umhverfis rafeindaský rafeindir neikvætt stöðugri kringum kjarnann skipt skeljar svigrúm hver skel geymt ákveðinn ystu skelinni kallast gildisskel efnafræðilega eiginleika hlutlausu atómi kjarnanum jafn þannig jákvæða neikvæða hleðslan jafnast atómið hefur enga heildarhleðslu einnig kallaður atómnúmer hvaða frumeind hvernig getum dregið meðal orkunotkun spara orku minnkum magn losnar virkjunum þessu orkusparandi tæki lýsingu einangra slökkva ljósum rafeindabúnaði þau notaðu bílar vörubílar helstu uppsprettur hjólreiðar fækka bílum veginum aftur dregur útblæstri ábyrgur úrgangi úrgangur brenndur niðurbrotinn hann skaðlegar lofttegundir fargaðu spilliefnum réttan endurvinna plast pappír gler mögulegt 4 orkugjafa endurnýjanlegir orkugjafar sólar vindorka valda lítilli engri styðjið orkufyrirtæki verkefni íhugið setja upp endurnýjanleg orkukerfi þínu 5 akið ef þarft skaltu ganga bílnum sé vel haldið forðast hraða hröðun hemlun lausagangi 6 meðvitaður vöruval sumar venjur gefa sér meiri en aðrar veldu umhverfisvænum umbúðum reyndu lágmarka þína úðabrúsa skaðleg þurftir erfiða ai aðstoðarmaður hef eigin persónulegu reynslu tilvist hins vegar forritaður ákvarðanir byggðar reikniritum rökfræði gögnum tímar lendi aðstæðum erfitt geta verið misvísandi upplýsingar margar mögulegar niðurstöður slíkum tilfellum hæfileika greina vega áhættu ávinning hvers valkosts komast niðurstöðu líklegast tilætluðum árangri\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Translate a new sentence\n",
+    "def translate_new_sentence(model, en_sentence, en_vocab, ic_vocab, max_len=MAX_LEN):\n",
+    "    model.eval()\n",
+    "    en_tensor = sentence_to_tensor(en_sentence, en_vocab, max_len).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    # Start with the <s> token as input to the decoder\n",
+    "    ic_input = torch.tensor([ic_vocab['<s>']]).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    translated_sentence = []\n",
+    "    with torch.no_grad():\n",
+    "        for _ in range(max_len):\n",
+    "            output = model(en_tensor, ic_input)\n",
+    "            output_token = output.argmax(dim=-1)[:, -1].item()  # Get the most likely next token\n",
+    "\n",
+    "            translated_sentence.append(output_token)\n",
+    "            if output_token == ic_vocab['</s>']:  # End token\n",
+    "                break\n",
+    "\n",
+    "            # Update the input for the next time step (use the predicted token)\n",
+    "            ic_input = torch.tensor([output_token]).unsqueeze(0).to(DEVICE)  # Convert output_token to tensor\n",
+    "\n",
+    "    # Convert token IDs back to words\n",
+    "    translated_sentence = [k for k, v in ic_vocab.items() if v in translated_sentence]\n",
+    "    return \" \".join(translated_sentence)\n",
+    "\n",
+    "# Example sentence translation\n",
+    "en_example_sentence = \"This is a test sentence.\"\n",
+    "translated_ic_sentence = translate_new_sentence(model, en_example_sentence, en_vocab, ic_vocab)\n",
+    "print(f\"Original: {en_example_sentence}\")\n",
+    "print(f\"Translated: {translated_ic_sentence}\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "YbfHsa5PpW8G"
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "N93ucaxdpW_d"
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "NWPzmQ3zpXCi"
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "HCxdDaispXHV"
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "pHS_C_VTpXKu"
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "lNvPqrwPpXNc"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

A2_Q9_Google_Colab_for_LSTM_based_translator.ipynb

@@ -0,0 +1,473 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "SApoUTbo2am6",
+    "outputId": "5b6b852f-890d-43d3-8a2c-56fff0a4363b"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Requirement already satisfied: sacrebleu in /usr/local/lib/python3.10/dist-packages (2.4.3)\n",
+      "Requirement already satisfied: portalocker in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (2.10.1)\n",
+      "Requirement already satisfied: regex in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (2024.9.11)\n",
+      "Requirement already satisfied: tabulate>=0.8.9 in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (0.9.0)\n",
+      "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (1.26.4)\n",
+      "Requirement already satisfied: colorama in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (0.4.6)\n",
+      "Requirement already satisfied: lxml in /usr/local/lib/python3.10/dist-packages (from sacrebleu) (5.3.0)\n"
+     ]
+    }
+   ],
+   "source": [
+    "!pip install sacrebleu\n",
+    "\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from torch.utils.data import DataLoader, Dataset\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import sacrebleu\n",
+    "import json\n",
+    "import csv\n",
+    "from collections import Counter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "id": "yQlU_Iua2cKa"
+   },
+   "outputs": [],
+   "source": [
+    "DEVICE = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+    "\n",
+    "\n",
+    "# Load the Icelandic_cleaned.json dataset\n",
+    "with open('/content/Icelandic_cleaned.json', 'r', encoding='utf-8') as f:\n",
+    "    data = json.load(f)\n",
+    "\n",
+    "# Extract the first 1,000 English and Icelandic sentences for BLEU and CHRF calculation\n",
+    "en_sentences = [entry['input'] for entry in data[:1000]]\n",
+    "ic_sentences = [entry['output'] for entry in data[:1000]]\n",
+    "\n",
+    "# Tokenizer and Vectorization\n",
+    "tokenizer = lambda x: x.split()\n",
+    "\n",
+    "def build_vocab(sentences):\n",
+    "    counter = Counter()\n",
+    "    for sentence in sentences:\n",
+    "        counter.update(tokenizer(sentence))\n",
+    "    return counter\n",
+    "\n",
+    "en_vocab = build_vocab(en_sentences)\n",
+    "ic_vocab = build_vocab(ic_sentences)\n",
+    "\n",
+    "# Adding special tokens\n",
+    "en_vocab = {'<s>': 1, '</s>': 2, '<pad>': 0, '<unk>': 3, **en_vocab}\n",
+    "ic_vocab = {'<s>': 1, '</s>': 2, '<pad>': 0, '<unk>': 3, **ic_vocab}\n",
+    "\n",
+    "def sentence_to_tensor(sentence, vocab, max_len=MAX_LEN):\n",
+    "    tokens = tokenizer(sentence)\n",
+    "    indices = [vocab.get(token, vocab['<unk>']) for token in tokens]\n",
+    "    indices = [vocab['<s>']] + indices + [vocab['</s>']]\n",
+    "    if len(indices) < max_len:\n",
+    "        indices += [vocab['<pad>']] * (max_len - len(indices))\n",
+    "    else:\n",
+    "        indices = indices[:max_len]\n",
+    "    return torch.tensor(indices)\n",
+    "\n",
+    "VOCAB_SIZE = 10000\n",
+    "EMBEDDING_DIM = 256\n",
+    "HIDDEN_DIM = 512\n",
+    "BATCH_SIZE = 32\n",
+    "NUM_EPOCHS = 10\n",
+    "MAX_LEN = 50\n",
+    "\n",
+    "# Prepare dataset and dataloaders\n",
+    "en_tensor_sentences = [sentence_to_tensor(s, en_vocab) for s in en_sentences]\n",
+    "ic_tensor_sentences = [sentence_to_tensor(s, ic_vocab) for s in ic_sentences]\n",
+    "\n",
+    "# Split data into training and validation sets (80% train, 20% validation)\n",
+    "train_size = int(0.8 * len(en_tensor_sentences))\n",
+    "train_en, val_en = en_tensor_sentences[:train_size], en_tensor_sentences[train_size:]\n",
+    "train_ic, val_ic = ic_tensor_sentences[:train_size], ic_tensor_sentences[train_size:]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "-cSiMFUW2wFf"
+   },
+   "outputs": [],
+   "source": [
+    "# Custom Dataset\n",
+    "class TranslationDataset(Dataset):\n",
+    "    def __init__(self, en_sentences, ic_sentences):\n",
+    "        self.en_sentences = en_sentences\n",
+    "        self.ic_sentences = ic_sentences\n",
+    "\n",
+    "    def __len__(self):\n",
+    "        return len(self.en_sentences)\n",
+    "\n",
+    "    def __getitem__(self, idx):\n",
+    "        return self.en_sentences[idx], self.ic_sentences[idx]\n",
+    "\n",
+    "# Prepare dataloader\n",
+    "train_dataset = TranslationDataset(train_en, train_ic)\n",
+    "val_dataset = TranslationDataset(val_en, val_ic)\n",
+    "\n",
+    "# Define a collate_fn to pad sequences dynamically\n",
+    "def collate_fn(batch):\n",
+    "    en_batch, ic_batch = zip(*batch)\n",
+    "    en_batch = torch.stack(en_batch, dim=0)\n",
+    "    ic_batch = torch.stack(ic_batch, dim=0)\n",
+    "    return en_batch, ic_batch\n",
+    "\n",
+    "train_dataloader = DataLoader(train_dataset, batch_size=BATCH_SIZE, shuffle=True, collate_fn=collate_fn)\n",
+    "val_dataloader = DataLoader(val_dataset, batch_size=BATCH_SIZE, shuffle=False, collate_fn=collate_fn)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "-dgY3hG521B1"
+   },
+   "outputs": [],
+   "source": [
+    "# LSTM Model\n",
+    "class LSTMModel(nn.Module):\n",
+    "    def __init__(self, input_dim, output_dim, embedding_dim, hidden_dim, num_layers=1):\n",
+    "        super(LSTMModel, self).__init__()\n",
+    "\n",
+    "        self.encoder_embedding = nn.Embedding(input_dim, embedding_dim)\n",
+    "        self.encoder_lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers, batch_first=True)\n",
+    "\n",
+    "        self.decoder_embedding = nn.Embedding(output_dim, embedding_dim)\n",
+    "        self.decoder_lstm = nn.LSTM(embedding_dim, hidden_dim, num_layers, batch_first=True)\n",
+    "        self.fc_out = nn.Linear(hidden_dim, output_dim)\n",
+    "\n",
+    "    def forward(self, src, trg):\n",
+    "        embedded_src = self.encoder_embedding(src)\n",
+    "        encoder_output, (hidden, cell) = self.encoder_lstm(embedded_src)\n",
+    "\n",
+    "        embedded_trg = self.decoder_embedding(trg)\n",
+    "        decoder_output, _ = self.decoder_lstm(embedded_trg, (hidden, cell))\n",
+    "\n",
+    "        output = self.fc_out(decoder_output)\n",
+    "        return output\n",
+    "\n",
+    "# Initialize the LSTM model\n",
+    "model = LSTMModel(len(en_vocab), len(ic_vocab), EMBEDDING_DIM, HIDDEN_DIM, num_layers=1).to(DEVICE)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "tA4A8Lfp0l1c",
+    "outputId": "d45efe1a-ff8f-40da-d276-c7089b7b9333"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10, Training Loss: 4.24646101474762, Validation Loss: 1.915126085281372\n",
+      "Epoch 2/10, Training Loss: 1.1425018000602722, Validation Loss: 0.5995665192604065\n",
+      "Epoch 3/10, Training Loss: 0.3298293137550354, Validation Loss: 0.16065824457577296\n",
+      "Epoch 4/10, Training Loss: 0.09441208809614182, Validation Loss: 0.05612730234861374\n",
+      "Epoch 5/10, Training Loss: 0.038212009370326996, Validation Loss: 0.029360934027603695\n",
+      "Epoch 6/10, Training Loss: 0.022309018671512602, Validation Loss: 0.01924761331507138\n",
+      "Epoch 7/10, Training Loss: 0.015515815429389478, Validation Loss: 0.014102236367762089\n",
+      "Epoch 8/10, Training Loss: 0.011751469224691391, Validation Loss: 0.011091723372893674\n",
+      "Epoch 9/10, Training Loss: 0.009352730493992567, Validation Loss: 0.00901335131909166\n",
+      "Epoch 10/10, Training Loss: 0.0077053593099117275, Validation Loss: 0.007507234279598508\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Define the loss function and optimizer\n",
+    "criterion = nn.CrossEntropyLoss(ignore_index=ic_vocab['<pad>'])\n",
+    "optimizer = optim.Adam(model.parameters(), lr=0.001)\n",
+    "\n",
+    "# Function to train the model\n",
+    "def train_model(model, train_dataloader, val_dataloader, optimizer, criterion, num_epochs=10):\n",
+    "    model.to(DEVICE)\n",
+    "    train_losses, val_losses = [], []\n",
+    "\n",
+    "    for epoch in range(num_epochs):\n",
+    "        model.train()\n",
+    "        epoch_train_loss = 0\n",
+    "        for en_batch, ic_batch in train_dataloader:\n",
+    "            en_batch, ic_batch = en_batch.to(DEVICE), ic_batch.to(DEVICE)\n",
+    "            ic_batch = ic_batch.long()\n",
+    "\n",
+    "            optimizer.zero_grad()\n",
+    "            output = model(en_batch, ic_batch)\n",
+    "\n",
+    "            output_dim = output.shape[-1]\n",
+    "            output = output.reshape(-1, output_dim)\n",
+    "            ic_batch = ic_batch.reshape(-1)\n",
+    "            loss = criterion(output, ic_batch)\n",
+    "\n",
+    "            loss.backward()\n",
+    "            optimizer.step()\n",
+    "\n",
+    "            epoch_train_loss += loss.item()\n",
+    "\n",
+    "        train_losses.append(epoch_train_loss / len(train_dataloader))\n",
+    "\n",
+    "        model.eval()\n",
+    "        epoch_val_loss = 0\n",
+    "        with torch.no_grad():\n",
+    "            for en_batch, ic_batch in val_dataloader:\n",
+    "                en_batch, ic_batch = en_batch.to(DEVICE), ic_batch.to(DEVICE)\n",
+    "                ic_batch = ic_batch.long()\n",
+    "\n",
+    "                output = model(en_batch, ic_batch)\n",
+    "                output_dim = output.shape[-1]\n",
+    "                output = output.reshape(-1, output_dim)\n",
+    "                ic_batch = ic_batch.reshape(-1)\n",
+    "\n",
+    "                loss = criterion(output, ic_batch)\n",
+    "                epoch_val_loss += loss.item()\n",
+    "\n",
+    "        val_losses.append(epoch_val_loss / len(val_dataloader))\n",
+    "\n",
+    "        print(f'Epoch {epoch+1}/{num_epochs}, Training Loss: {train_losses[-1]}, Validation Loss: {val_losses[-1]}')\n",
+    "\n",
+    "    return train_losses, val_losses\n",
+    "\n",
+    "train_losses, val_losses = train_model(model, train_dataloader, val_dataloader, optimizer, criterion, num_epochs=NUM_EPOCHS)\n",
+    "\n",
+    "# Save the trained model\n",
+    "torch.save(model.state_dict(), 'lstm_Icendanic_model.pth')\n",
+    "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 564
+    },
+    "id": "QZfm6mkBKtGq",
+    "outputId": "c6d0d436-cd99-4aad-fe29-e823217011a3"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Set figure size before plotting\n",
+    "plt.figure(figsize=(12, 6))  # Adjust the size as desired, e.g., 12x6 inches\n",
+    "\n",
+    "# Plot training and validation losses\n",
+    "plt.plot(train_losses, label=\"Training Loss\")\n",
+    "plt.plot(val_losses, label=\"Validation Loss\")\n",
+    "plt.xlabel(\"Epochs\")\n",
+    "plt.ylabel(\"Loss\")\n",
+    "plt.legend()\n",
+    "plt.title(\"Training and Validation Losses for LTSM\")\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "Tzcfd66K095C",
+    "outputId": "9868591d-54a3-494b-ba6d-a18dccaf9ca3"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "BLEU and CHRF scores saved to 'Seq2Seq_BLEU_CHRF_scores.csv'\n"
+     ]
+    }
+   ],
+   "source": [
+    "def translate_new_sentence(model, sentence, src_vocab, tgt_vocab, max_len=MAX_LEN):\n",
+    "    # Prepare input tensor for the source sentence (English)\n",
+    "    model.eval()  # Set model to evaluation mode\n",
+    "    en_indices = [src_vocab.get(word, src_vocab['<unk>']) for word in sentence.split()]  # Handle unknown words\n",
+    "    en_tensor = torch.tensor(en_indices).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    # Initialize target sentence for translation (Icelandic) with start token\n",
+    "    tgt_tensor = torch.tensor([tgt_vocab['<s>']]).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    translated_sentence = []\n",
+    "\n",
+    "    for _ in range(max_len):\n",
+    "        with torch.no_grad():\n",
+    "            output = model(en_tensor, tgt_tensor)\n",
+    "\n",
+    "        # Get the last output token's prediction (the next word)\n",
+    "        output_token = output.argmax(dim=-1)[:, -1]\n",
+    "\n",
+    "        # Get the predicted word from the target vocabulary\n",
+    "        output_token_item = output_token.item()\n",
+    "\n",
+    "        # Check if the token is within the target vocabulary range\n",
+    "        if output_token_item not in tgt_vocab.values():\n",
+    "            translated_word = '<unk>'  # Map to <unk> if not found\n",
+    "        else:\n",
+    "            translated_word = list(tgt_vocab.keys())[list(tgt_vocab.values()).index(output_token_item)]\n",
+    "\n",
+    "        # Append predicted word to the translated sentence\n",
+    "        translated_sentence.append(translated_word)\n",
+    "\n",
+    "        # If we encounter an end token, stop the translation\n",
+    "        if translated_word == '</s>':\n",
+    "            break\n",
+    "\n",
+    "        # Update tgt_tensor for next prediction\n",
+    "        tgt_tensor = torch.cat((tgt_tensor, output_token.unsqueeze(0)), dim=-1)\n",
+    "\n",
+    "    return ' '.join(translated_sentence)\n",
+    "\n",
+    "# BLEU and CHRF Scores Calculation\n",
+    "def calculate_bleu_chrf(en_sentences, ic_sentences, model, en_vocab, ic_vocab, max_len=MAX_LEN):\n",
+    "    bleu_scores = []\n",
+    "    chrf_scores = []\n",
+    "\n",
+    "    for en_sentence, ic_sentence in zip(en_sentences, ic_sentences):\n",
+    "        translated_sentence = translate_new_sentence(model, en_sentence, en_vocab, ic_vocab, max_len)\n",
+    "\n",
+    "        # Calculate BLEU score\n",
+    "        bleu_score = sacrebleu.corpus_bleu([translated_sentence], [[ic_sentence]]).score\n",
+    "        bleu_scores.append(bleu_score)\n",
+    "\n",
+    "        # Calculate CHRF score\n",
+    "        chrf_score = sacrebleu.corpus_chrf([translated_sentence], [[ic_sentence]]).score\n",
+    "        chrf_scores.append(chrf_score)\n",
+    "\n",
+    "    return bleu_scores, chrf_scores\n",
+    "\n",
+    "# Calculate BLEU and CHRF for the translation model\n",
+    "lstm_bleu_scores, lstm_chrf_scores = calculate_bleu_chrf(en_sentences, ic_sentences, model, en_vocab, ic_vocab, max_len=MAX_LEN)\n",
+    "\n",
+    "# Save BLEU and CHRF scores to CSV\n",
+    "import csv\n",
+    "\n",
+    "with open('LTSM_BLEU_CHRF_scores.csv', mode='w', newline='', encoding='utf-8') as file:\n",
+    "    writer = csv.writer(file)\n",
+    "    writer.writerow([\"BLEU Score\", \"CHRF Score\"])\n",
+    "    for bleu, chrf in zip(lstm_bleu_scores, lstm_chrf_scores):\n",
+    "        writer.writerow([bleu, chrf])\n",
+    "\n",
+    "print(\"BLEU and CHRF scores saved to 'LTSM_BLEU_CHRF_scores.csv'\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "nyVtO9D02Qp5",
+    "outputId": "1e52fbf8-3a94-4bf7-ab83-bbbb45051124"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Original: This is a test sentence.\n",
+      "Translated: <s> gefðu þrjú ráð halda heilsu borðaðu hollt næringarríkt mataræði gakktu máltíðirnar þínar innihaldi margs konar ávexti grænmeti magurt prótein heilkorn holla fitu þetta veita líkamanum nauðsynleg næringarefni virka best hjálpað koma veg langvinna sjúkdóma taktu þátt reglulegri hreyfing mikilvæg viðhalda sterkum beinum vöðvum hjarta æðaheilbrigði minnsta kosti 150 hóflegri þolþjálfun 75 öflugri viku fáðu fá gæðasvefn skiptir sköpum andlega vellíðan stjórna skapi bæta vitræna virkni heilbrigðan vöxt ónæmisvirkni 79 nóttu hverjir gulur þessir litir kallaðir blanda öðrum litum alla aðra liti sameina ýmsum hlutföllum auklitakerfinu notað ljós grænn rgb byggingu atóm grunnbygging alls efnis samsett þremur tegundum agna rafeindum lýsa má uppbyggingu miðjunni umkringdur rafeindaskýi kjarni gerður róteindir jákvætt nifteindir hlutlausar án hleðslu báðar þessar staðsettar miðju inniheldur mestan hluta umhverfis rafeindaský rafeindir neikvætt stöðugri kringum kjarnann skipt skeljar svigrúm hver skel geymt ákveðinn ystu skelinni kallast gildisskel efnafræðilega eiginleika hlutlausu atómi kjarnanum jafn þannig jákvæða neikvæða hleðslan jafnast atómið hefur enga heildarhleðslu einnig kallaður atómnúmer hvaða frumeind hvernig getum dregið meðal orkunotkun spara orku minnkum magn losnar virkjunum þessu orkusparandi tæki lýsingu einangra slökkva ljósum rafeindabúnaði þau notaðu bílar vörubílar helstu uppsprettur hjólreiðar fækka bílum veginum aftur dregur útblæstri ábyrgur úrgangi úrgangur brenndur niðurbrotinn hann skaðlegar lofttegundir fargaðu spilliefnum réttan endurvinna plast pappír gler mögulegt 4 orkugjafa endurnýjanlegir orkugjafar sólar vindorka valda lítilli engri styðjið orkufyrirtæki verkefni íhugið setja upp endurnýjanleg orkukerfi þínu 5 akið ef þarft skaltu ganga bílnum sé vel haldið forðast hraða hröðun hemlun lausagangi 6 meðvitaður vöruval sumar venjur gefa sér meiri en aðrar veldu umhverfisvænum umbúðum reyndu lágmarka þína úðabrúsa skaðleg þurftir erfiða ai aðstoðarmaður hef eigin persónulegu reynslu tilvist hins vegar forritaður ákvarðanir byggðar reikniritum rökfræði gögnum tímar lendi aðstæðum erfitt geta verið misvísandi upplýsingar margar mögulegar niðurstöður slíkum tilfellum hæfileika greina vega áhættu ávinning hvers valkosts komast niðurstöðu líklegast tilætluðum árangri\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Translate a new sentence\n",
+    "def translate_new_sentence(model, en_sentence, en_vocab, ic_vocab, max_len=MAX_LEN):\n",
+    "    model.eval()\n",
+    "    en_tensor = sentence_to_tensor(en_sentence, en_vocab, max_len).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    # Start with the <s> token as input to the decoder\n",
+    "    ic_input = torch.tensor([ic_vocab['<s>']]).unsqueeze(0).to(DEVICE)\n",
+    "\n",
+    "    translated_sentence = []\n",
+    "    with torch.no_grad():\n",
+    "        for _ in range(max_len):\n",
+    "            output = model(en_tensor, ic_input)\n",
+    "            output_token = output.argmax(dim=-1)[:, -1].item()  # Get the most likely next token\n",
+    "\n",
+    "            translated_sentence.append(output_token)\n",
+    "            if output_token == ic_vocab['</s>']:  # End token\n",
+    "                break\n",
+    "\n",
+    "            # Update the input for the next time step (use the predicted token)\n",
+    "            ic_input = torch.tensor([output_token]).unsqueeze(0).to(DEVICE)  # Convert output_token to tensor\n",
+    "\n",
+    "    # Convert token IDs back to words\n",
+    "    translated_sentence = [k for k, v in ic_vocab.items() if v in translated_sentence]\n",
+    "    return \" \".join(translated_sentence)\n",
+    "\n",
+    "# Example sentence translation\n",
+    "en_example_sentence = \"This is a test sentence.\"\n",
+    "translated_ic_sentence = translate_new_sentence(model, en_example_sentence, en_vocab, ic_vocab)\n",
+    "print(f\"Original: {en_example_sentence}\")\n",
+    "print(f\"Translated: {translated_ic_sentence}\")\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "colab": {
+   "provenance": []
+  },
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}

Colab Links.txt

@@ -0,0 +1,6 @@
+LTSM;;   
+https://colab.research.google.com/drive/1U0-d3rWZp_z-p7r3L4yE1vxeS3RL-NfG?usp=sharing
+
+Seq2seq
+
+https://colab.research.google.com/drive/11mcIrgKqm536dE0vL-5zMg-pPQFnSQG4?usp=sharing