MTL-question-generation

The MTL-question-generation 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-question-generation is supervised pre-trained using a mixture of labeled question generation datasets. It is a variant (Single) of our main MVP model. It follows a standard Transformer encoder-decoder architecture.

MTL-question-generation is specially designed for question generation tasks, such as SQuAD and CoQA.

Example

>>> from transformers import MvpTokenizer, MvpForConditionalGeneration

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

>>> inputs = tokenizer(
...     "Generate the question based on the answer: boxing [X_SEP] A bolo punch is a punch used in martial arts . A hook is a punch in boxing .",
...     return_tensors="pt",
... )
>>> generated_ids = model.generate(**inputs)
>>> tokenizer.batch_decode(generated_ids, skip_special_tokens=True)
['A bolo punch and a hook are both punches used in what sport?]

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},
}
Downloads last month
10
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.