pszemraj commited on
Commit
6351371
·
1 Parent(s): 33353d8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -23
README.md CHANGED
@@ -41,54 +41,31 @@ then model will respond, ideally with person beta: "response text"
41
 
42
  - the default inference API examples should work _okay_
43
  - an ideal test would be explicitly adding `person beta` to the **end** of the prompt text. The model is forced to respond to the entered chat prompt instead of adding to the entered prompt and then responding to that (which may cut off the response text due to the Inference API limits).
44
-
45
  ## citations
46
-
47
  ```
48
  @inproceedings{dinan2019wizard,
49
-
50
  author={Emily Dinan and Stephen Roller and Kurt Shuster and Angela Fan and Michael Auli and Jason Weston},
51
-
52
  title={{W}izard of {W}ikipedia: Knowledge-powered Conversational Agents},
53
-
54
  booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
55
-
56
  year={2019},
57
-
58
  }
59
 
60
  @inproceedings{li-etal-2017-dailydialog,
61
-
62
  title = "{D}aily{D}ialog: A Manually Labelled Multi-turn Dialogue Dataset",
63
-
64
  author = "Li, Yanran and
65
-
66
  Su, Hui and
67
-
68
  Shen, Xiaoyu and
69
-
70
  Li, Wenjie and
71
-
72
  Cao, Ziqiang and
73
-
74
  Niu, Shuzi",
75
-
76
  booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
77
-
78
  month = nov,
79
-
80
  year = "2017",
81
-
82
  address = "Taipei, Taiwan",
83
-
84
  publisher = "Asian Federation of Natural Language Processing",
85
-
86
  url = "https://aclanthology.org/I17-1099",
87
-
88
  pages = "986--995",
89
-
90
  abstract = "We develop a high-quality multi-turn dialog dataset, \textbf{DailyDialog}, which is intriguing in several aspects. The language is human-written and less noisy. The dialogues in the dataset reflect our daily communication way and cover various topics about our daily life. We also manually label the developed dataset with communication intention and emotion information. Then, we evaluate existing approaches on DailyDialog dataset and hope it benefit the research field of dialog systems. The dataset is available on \url{http://yanran.li/dailydialog}",
91
-
92
  }
93
  ```
94
 
 
41
 
42
  - the default inference API examples should work _okay_
43
  - an ideal test would be explicitly adding `person beta` to the **end** of the prompt text. The model is forced to respond to the entered chat prompt instead of adding to the entered prompt and then responding to that (which may cut off the response text due to the Inference API limits).
 
44
  ## citations
 
45
  ```
46
  @inproceedings{dinan2019wizard,
 
47
  author={Emily Dinan and Stephen Roller and Kurt Shuster and Angela Fan and Michael Auli and Jason Weston},
 
48
  title={{W}izard of {W}ikipedia: Knowledge-powered Conversational Agents},
 
49
  booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
 
50
  year={2019},
 
51
  }
52
 
53
  @inproceedings{li-etal-2017-dailydialog,
 
54
  title = "{D}aily{D}ialog: A Manually Labelled Multi-turn Dialogue Dataset",
 
55
  author = "Li, Yanran and
 
56
  Su, Hui and
 
57
  Shen, Xiaoyu and
 
58
  Li, Wenjie and
 
59
  Cao, Ziqiang and
 
60
  Niu, Shuzi",
 
61
  booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
 
62
  month = nov,
 
63
  year = "2017",
 
64
  address = "Taipei, Taiwan",
 
65
  publisher = "Asian Federation of Natural Language Processing",
 
66
  url = "https://aclanthology.org/I17-1099",
 
67
  pages = "986--995",
 
68
  abstract = "We develop a high-quality multi-turn dialog dataset, \textbf{DailyDialog}, which is intriguing in several aspects. The language is human-written and less noisy. The dialogues in the dataset reflect our daily communication way and cover various topics about our daily life. We also manually label the developed dataset with communication intention and emotion information. Then, we evaluate existing approaches on DailyDialog dataset and hope it benefit the research field of dialog systems. The dataset is available on \url{http://yanran.li/dailydialog}",
 
69
  }
70
  ```
71