StevenTang commited on
Commit
4c2aabe
1 Parent(s): 2ab7fd1

Update README

Browse files
Files changed (1) hide show
  1. README.md +34 -2
README.md CHANGED
@@ -14,12 +14,12 @@ widget:
14
  ---
15
 
16
  # MVP-question-answering
17
- The MVP-question-answering model was proposed in [**MVP: Multi-task Supervised Pre-training for Natural Language Generation**](https://github.com/RUCAIBox/MVP/blob/main/paper.pdf) by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen.
18
 
19
  The detailed information and instructions can be found [https://github.com/RUCAIBox/MVP](https://github.com/RUCAIBox/MVP).
20
 
21
  ## Model Description
22
- MVP-question-answering is a prompt-based model that MVP is further equipped with prompts pre-trained using labeled question answering datasets. It is a variant (MVP+S) of our main MVP model. It follows a Transformer encoder-decoder architecture with layer-wise prompts.
23
 
24
  MVP-question-answering is specially designed for question answering tasks, such as reading comprehension (SQuAD), conversational question answering (CoQA) and closed-book question-answering (Natural Questions).
25
 
@@ -39,4 +39,36 @@ MVP-question-answering is specially designed for question answering tasks, such
39
  ['Portugal']
40
  ```
41
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
42
  ## Citation
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  # MVP-question-answering
17
+ The MVP-question-answering model was proposed in [**MVP: Multi-task Supervised Pre-training for Natural Language Generation**](https://arxiv.org/abs/2206.12131) by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen.
18
 
19
  The detailed information and instructions can be found [https://github.com/RUCAIBox/MVP](https://github.com/RUCAIBox/MVP).
20
 
21
  ## Model Description
22
+ MVP-question-answering is a prompt-based model that MVP is further equipped with prompts pre-trained using labeled question answering datasets. It is a variant (MVP+S) of our [MVP](https://huggingface.co/RUCAIBox/mvp) [MVP](https://huggingface.co/RUCAIBox/mvp) model. It follows a Transformer encoder-decoder architecture with layer-wise prompts.
23
 
24
  MVP-question-answering is specially designed for question answering tasks, such as reading comprehension (SQuAD), conversational question answering (CoQA) and closed-book question-answering (Natural Questions).
25
 
 
39
  ['Portugal']
40
  ```
41
 
42
+ ## Related Models
43
+ **MVP**: [https://huggingface.co/RUCAIBox/mvp](https://huggingface.co/RUCAIBox/mvp).
44
+
45
+ **Prompt-based models**:
46
+
47
+ - MVP-multi-task: [https://huggingface.co/RUCAIBox/mvp-multi-task](https://huggingface.co/RUCAIBox/mvp-multi-task).
48
+ - MVP-summarization: [https://huggingface.co/RUCAIBox/mvp-summarization](https://huggingface.co/RUCAIBox/mvp-summarization).
49
+ - MVP-open-dialog: [https://huggingface.co/RUCAIBox/mvp-open-dialog](https://huggingface.co/RUCAIBox/mvp-open-dialog).
50
+ - MVP-data-to-text: [https://huggingface.co/RUCAIBox/mvp-data-to-text](https://huggingface.co/RUCAIBox/mvp-data-to-text).
51
+ - MVP-story: [https://huggingface.co/RUCAIBox/mvp-story](https://huggingface.co/RUCAIBox/mvp-story).
52
+ - MVP-question-answering: [https://huggingface.co/RUCAIBox/mvp-question-answering](https://huggingface.co/RUCAIBox/mvp-question-answering).
53
+ - MVP-question-generation: [https://huggingface.co/RUCAIBox/mvp-question-generation](https://huggingface.co/RUCAIBox/mvp-question-generation).
54
+ - MVP-task-dialog: [https://huggingface.co/RUCAIBox/mvp-task-dialog](https://huggingface.co/RUCAIBox/mvp-task-dialog).
55
+
56
+ **Multi-task models**:
57
+ - MTL-summarization: [https://huggingface.co/RUCAIBox/mtl-summarization](https://huggingface.co/RUCAIBox/mtl-summarization).
58
+ - MTL-open-dialog: [https://huggingface.co/RUCAIBox/mtl-open-dialog](https://huggingface.co/RUCAIBox/mtl-open-dialog).
59
+ - MTL-data-to-text: [https://huggingface.co/RUCAIBox/mtl-data-to-text](https://huggingface.co/RUCAIBox/mtl-data-to-text).
60
+ - MTL-story: [https://huggingface.co/RUCAIBox/mtl-story](https://huggingface.co/RUCAIBox/mtl-story).
61
+ - MTL-question-answering: [https://huggingface.co/RUCAIBox/mtl-question-answering](https://huggingface.co/RUCAIBox/mtl-question-answering).
62
+ - MTL-question-generation: [https://huggingface.co/RUCAIBox/mtl-question-generation](https://huggingface.co/RUCAIBox/mtl-question-generation).
63
+ - MTL-task-dialog: [https://huggingface.co/RUCAIBox/mtl-task-dialog](https://huggingface.co/RUCAIBox/mtl-task-dialog).
64
+
65
  ## Citation
66
+ ```bibtex
67
+ @article{tang2022mvp,
68
+ title={MVP: Multi-task Supervised Pre-training for Natural Language Generation},
69
+ author={Tang, Tianyi and Li, Junyi and Zhao, Wayne Xin and Wen, Ji-Rong},
70
+ journal={arXiv preprint arXiv:2206.12131},
71
+ year={2022},
72
+ url={https://arxiv.org/abs/2206.12131},
73
+ }
74
+ ```