Hugging Face's logo

RUCAIBox
/
mtl-task-dialog

Text2Text Generation
Transformers
PyTorch
English
mvp
text-generation
Inference Endpoints
Model card Files Community
mtl-task-dialog / README.md
StevenTang's picture
StevenTang
Update README
8b1c1a9
preview code
|
raw
history blame contribute delete
4.27 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - text-generation
  - text2text-generation
pipeline_tag: text2text-generation
widget:
  - 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.
    example_title: Example1
  - 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.
    example_title: Example2
  - 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.
    example_title: Example3

MTL-task-dialog

The MTL-task-dialog model was proposed in MVP: Multi-task Supervised Pre-training for Natural Language Generation by Tianyi Tang, Junyi Li, Wayne Xin Zhao and Ji-Rong Wen.

The detailed information and instructions can be found https://github.com/RUCAIBox/MVP.

Model Description

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 model. It follows a standard Transformer encoder-decoder architecture.

MTL-task-dialog is specially designed for task-oriented system tasks, such as MultiWOZ.

Example 

>>> from transformers import MvpTokenizer, MvpForConditionalGeneration

>>> tokenizer = MvpTokenizer.from_pretrained("RUCAIBox/mvp")
>>> model = MvpForConditionalGeneration.from_pretrained("RUCAIBox/mtl-task-dialog")

>>> inputs = tokenizer(
...     "Given the task dialog: System response [X_SEP] I'm looking for a affordable BBQ restaurant in Dallas for a large group of guest.",
...     return_tensors="pt",
... )
>>> generated_ids = model.generate(**inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
['What date and time would you like to go?']

Related Models

MVP: https://huggingface.co/RUCAIBox/mvp.

Prompt-based models:

Multi-task models:

Citation 

@article{tang2022mvp,
  title={MVP: Multi-task Supervised Pre-training for Natural Language Generation},
  author={Tang, Tianyi and Li, Junyi and Zhao, Wayne Xin and Wen, Ji-Rong},
  journal={arXiv preprint arXiv:2206.12131},
  year={2022},
  url={https://arxiv.org/abs/2206.12131},
}