pszemraj commited on
Commit
0f5dcd0
1 Parent(s): 2e551a3

:memo: add citations

Browse files
Files changed (1) hide show
  1. README.md +50 -1
README.md CHANGED
@@ -19,4 +19,53 @@ The dataset was tokenized and fed to the model as a conversation between two spe
19
  ## examples
20
 
21
  - the default inference API examples should work _okay_
22
- - an ideal test would be explicitly adding `person beta` into the prompt text the model is forced to respond to instead of adding onto the entered prompt.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  ## examples
20
 
21
  - the default inference API examples should work _okay_
22
+ - an ideal test would be explicitly adding `person beta` into the prompt text the model is forced to respond to instead of adding onto the entered prompt.
23
+
24
+ ## citations
25
+
26
+ @inproceedings{dinan2019wizard,
27
+
28
+ author={Emily Dinan and Stephen Roller and Kurt Shuster and Angela Fan and Michael Auli and Jason Weston},
29
+
30
+ title={{W}izard of {W}ikipedia: Knowledge-powered Conversational Agents},
31
+
32
+ booktitle = {Proceedings of the International Conference on Learning Representations (ICLR)},
33
+
34
+ year={2019},
35
+
36
+ }
37
+
38
+ @inproceedings{li-etal-2017-dailydialog,
39
+
40
+ title = "{D}aily{D}ialog: A Manually Labelled Multi-turn Dialogue Dataset",
41
+
42
+ author = "Li, Yanran and
43
+
44
+ Su, Hui and
45
+
46
+ Shen, Xiaoyu and
47
+
48
+ Li, Wenjie and
49
+
50
+ Cao, Ziqiang and
51
+
52
+ Niu, Shuzi",
53
+
54
+ booktitle = "Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
55
+
56
+ month = nov,
57
+
58
+ year = "2017",
59
+
60
+ address = "Taipei, Taiwan",
61
+
62
+ publisher = "Asian Federation of Natural Language Processing",
63
+
64
+ url = "https://aclanthology.org/I17-1099",
65
+
66
+ pages = "986--995",
67
+
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
+