Unified Language Model Pre-training for Natural Language Understanding and Generation
Abstract
This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieves new state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35.75 (0.86 absolute improvement), the CoQA generative question answering F1 score to 82.5 (37.1 absolute improvement), the SQuAD question generation BLEU-4 to 22.12 (3.75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2.67 (human performance is 2.65). The code and pre-trained models are available at https://github.com/microsoft/unilm.
Cite
@article{arxiv.1905.03197,
title = {Unified Language Model Pre-training for Natural Language Understanding and Generation},
author = {Li Dong and Nan Yang and Wenhui Wang and Furu Wei and Xiaodong Liu and Yu Wang and Jianfeng Gao and Ming Zhou and Hsiao-Wuen Hon},
journal= {arXiv preprint arXiv:1905.03197},
year = {2019}
}
Comments
Accepted by NeurIPS-19. Code and pre-trained models: https://github.com/microsoft/unilm