add eval

eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_ruquad.default.json

@@ -0,0 +1 @@
+{"test": {"QAAlignedF1Score (BERTScore)": 0.8013157037498974, "QAAlignedRecall (BERTScore)": 0.8442430440103075, "QAAlignedPrecision (BERTScore)": 0.7639532969736202, "QAAlignedF1Score (MoverScore)": 0.5718832506417842, "QAAlignedRecall (MoverScore)": 0.6060961159311626, "QAAlignedPrecision (MoverScore)": 0.5439067021893125, "Bleu_1": 0.11259560425044375, "Bleu_2": 0.06480994917400033, "Bleu_3": 0.04125633604208646, "Bleu_4": 0.026675568185441065, "METEOR": 0.22502064067084465, "ROUGE_L": 0.1619108882248903, "BERTScore": 0.687269137915848, "MoverScore": 0.5216012300104566}, "validation": {"QAAlignedF1Score (BERTScore)": 0.8016260224489642, "QAAlignedRecall (BERTScore)": 0.8451422758626326, "QAAlignedPrecision (BERTScore)": 0.7638218394271081, "QAAlignedF1Score (MoverScore)": 0.5716992361089386, "QAAlignedRecall (MoverScore)": 0.6056883954044378, "QAAlignedPrecision (MoverScore)": 0.5438196277362174, "Bleu_1": 0.11047520223768369, "Bleu_2": 0.06312074232947483, "Bleu_3": 0.039835093920407724, "Bleu_4": 0.025215345491863574, "METEOR": 0.223002383146665, "ROUGE_L": 0.1605553423023698, "BERTScore": 0.6855676182054602, "MoverScore": 0.521003870724837}}

eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_ruquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.4663756228777851, "Bleu_2": 0.4155876662534071, "Bleu_3": 0.36972655230630713, "Bleu_4": 0.3239451532174696, "METEOR": 0.3895656081425938, "ROUGE_L": 0.511855943428274, "BERTScore": 0.8678218379107802, "MoverScore": 0.7499888979799185, "AnswerF1Score": 65.47494176458382, "AnswerExactMatch": 44.71803018268467}, "test": {"Bleu_1": 0.4572117316191037, "Bleu_2": 0.40805360546484093, "Bleu_3": 0.36246310848474206, "Bleu_4": 0.3166407646029917, "METEOR": 0.38788942160800594, "ROUGE_L": 0.5003934696938921, "BERTScore": 0.8631733495496492, "MoverScore": 0.7474806806428033, "AnswerF1Score": 64.48641046915944, "AnswerExactMatch": 44.42017474185862}}

eval/metric.first.sentence.paragraph_answer.question.lmqg_qg_ruquad.default.json

@@ -0,0 +1 @@
+{"validation": {"Bleu_1": 0.3619407768234765, "Bleu_2": 0.29033425008731933, "Bleu_3": 0.23641200890016237, "Bleu_4": 0.19411994704139615, "METEOR": 0.30143989361267076, "ROUGE_L": 0.3523491452333354, "BERTScore": 0.8785415228134246, "MoverScore": 0.6658989469986961}, "test": {"Bleu_1": 0.36703296703295923, "Bleu_2": 0.2951238076514465, "Bleu_3": 0.24152908294283337, "Bleu_4": 0.1993995892697433, "METEOR": 0.3025516496773823, "ROUGE_L": 0.3546212544292116, "BERTScore": 0.8789150772738192, "MoverScore": 0.6658625835140267}}