Pretraining-Based Natural Language Generation for Text Summarization

By Haoyu Zhang, Yeyun Gong, Yu Yan, Nan Duan, Jianjun Xu, Ji Wang, Ming Gong, M. Zhou. 2019

228 citations recorded by the source corpus.

In this paper, we propose a novel pretraining-based encoder-decoder framework, which can generate the output sequence based on the input sequence in a two-stage manner. For the encoder of our model, we encode the input sequence into context representations using BERT. For the decoder, there are two stages in our model, in the first stage, we use a Transformer-based decoder to generate a draft output sequence. In the second stage, we mask each word of the draft sequence and feed it to BERT, then by combining the input sequence and the draft representation generated by BERT, we use a Transformer-based decoder to predict the refined word for each masked position. To the best of our knowledge, our approach is the first method which applies the BERT into text generation tasks. As the first step in this direction, we evaluate our proposed method on the text summarization task. Experimental results show that our model achieves new state-of-the-art on both CNN/Daily Mail and New York Times datasets.

Subfields: Artificial Intelligence, Natural Language Processing, Summarization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Mohit Bansal
  2. Graham Neubig
  3. Jianfeng Gao
  4. Caiming Xiong
  5. Richard Socher
  6. Luke S. Zettlemoyer
  7. Percy Liang
  8. Pengfei Liu

In Natural Language Processing

  1. Graham Neubig
  2. Pengfei Liu
  3. Mohit Bansal
  4. Xipeng Qiu
  5. Caiming Xiong
  6. Richard Socher
  7. Jianfeng Gao
  8. Kyunghyun Cho

In Summarization

  1. Yixin Liu
  2. Pengfei Liu
  3. Graham Neubig
  4. Iwona Mochol
  5. Wang Ling
  6. Bryan McCann
  7. Aleksander Wawer
  8. Xipeng Qiu

Citations in the corpus