Pretraining-Based Natural Language Generation for Text Summarization

Haoyu Zhang, Jingjing Cai, Jianjun Xu, Ji Wang


Abstract
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.
Anthology ID:
K19-1074
Volume:
Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
789–797
Language:
URL:
https://www.aclweb.org/anthology/K19-1074
DOI:
10.18653/v1/K19-1074
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/K19-1074.pdf