StevenTang commited on
Commit
50b181e
1 Parent(s): 6b173a8

Update README

Browse files
Files changed (1) hide show
  1. README.md +44 -0
README.md ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - text-generation
7
+ - text2text-generation
8
+ pipeline_tag: text2text-generation
9
+ widget:
10
+ - text: "Given the task dialog: Belief state [X_SEP] I'm looking for a affordable BBQ restaurant in Dallas for a large group of guest."
11
+ example_title: "Example1"
12
+ - text: "Given the task dialog: Dialogue action [X_SEP] I'm looking for a affordable BBQ restaurant in Dallas for a large group of guest."
13
+ example_title: "Example2"
14
+ - text: "Given the task dialog: System response [X_SEP] I'm looking for a affordable BBQ restaurant in Dallas for a large group of guest."
15
+ example_title: "Example3"
16
+ ---
17
+
18
+ # MTL-task-dialog
19
+ The MTL-task-dialog 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.
20
+
21
+ The detailed information and instructions can be found [https://github.com/RUCAIBox/MVP](https://github.com/RUCAIBox/MVP).
22
+
23
+ ## Model Description
24
+ MTL-task-dialog is supervised pre-trained using a mixture of labeled task-oriented system datasets. It is a variant (Single) of our main [MVP](https://huggingface.co/RUCAIBox/mvp) model. It follows a standard Transformer encoder-decoder architecture.
25
+
26
+ MTL-task-dialog is specially designed for task-oriented system tasks, such as MultiWOZ.
27
+
28
+ ## Example
29
+ ```python
30
+ >>> from transformers import MvpTokenizer, MvpForConditionalGeneration
31
+
32
+ >>> tokenizer = MvpTokenizer.from_pretrained("RUCAIBox/mvp")
33
+ >>> model = MvpForConditionalGeneration.from_pretrained("RUCAIBox/mtl-task-dialog")
34
+
35
+ >>> inputs = tokenizer(
36
+ ... "Given the task dialog: System response [X_SEP] I'm looking for a affordable BBQ restaurant in Dallas for a large group of guest.",
37
+ ... return_tensors="pt",
38
+ ... )
39
+ >>> generated_ids = model.generate(**inputs)
40
+ >>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
41
+ ['What date and time would you like to go?']
42
+ ```
43
+
44
+ ## Citation