Unified Language Model Pre-training for Natural Language Understanding and Generation

Code

• github.com/microsoft/unilm
  OfficialIn paperpytorch★ 22,060
• github.com/facebookresearch/data2vec_vision
  pytorch★ 80
• github.com/KnightZhang625/BERT_TF
  tf★ 0
• github.com/YunwenTechnology/Unilm
  pytorch★ 0
• github.com/fuqiang-git-hub/unilmv1-Paddle
  paddle★ 0
• github.com/robinsongh381/unilm_pytorch_korean
  pytorch★ 0
• github.com/jiaruncao/BioCopyMechanism
  none★ 0
• github.com/LeonZh0u/Chatbot
  pytorch★ 0
• github.com/uabinf/nlp-fall-2019-project-anuradha_shinjitha
  none★ 0

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.

Tasks

Benchmark Results

Reproductions