Pretraining-Based Natural Language Generation for Text Summarization

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.

[1]  Bowen Zhou,et al.  SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents , 2016, AAAI.

[2]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[3]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Christopher D. Manning,et al.  Get To The Point: Summarization with Pointer-Generator Networks , 2017, ACL.

[5]  Xinyan Xiao,et al.  Improving Neural Abstractive Document Summarization with Explicit Information Selection Modeling , 2018, EMNLP.

[6]  Hang Li,et al.  “ Tony ” DNN Embedding for “ Tony ” Selective Read for “ Tony ” ( a ) Attention-based Encoder-Decoder ( RNNSearch ) ( c ) State Update s 4 SourceVocabulary Softmax Prob , 2016 .

[7]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[8]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[9]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[10]  Tiejun Zhao,et al.  Neural Document Summarization by Jointly Learning to Score and Select Sentences , 2018, ACL.

[11]  Alec Radford,et al.  Improving Language Understanding by Generative Pre-Training , 2018 .

[12]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[13]  Mirella Lapata,et al.  Neural Latent Extractive Document Summarization , 2018, EMNLP.

[14]  Mirella Lapata,et al.  Ranking Sentences for Extractive Summarization with Reinforcement Learning , 2018, NAACL.

[15]  Ming-Wei Chang,et al.  Language Model Pre-training for Hierarchical Document Representations , 2019, ArXiv.

[16]  Yejin Choi,et al.  Deep Communicating Agents for Abstractive Summarization , 2018, NAACL.

[17]  Dan Klein,et al.  Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints , 2016, ACL.

[18]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[19]  Zhiyuan Liu,et al.  DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization , 2018, AAAI.

[20]  Richard Socher,et al.  Improving Abstraction in Text Summarization , 2018, EMNLP.

[21]  Richard Socher,et al.  A Deep Reinforced Model for Abstractive Summarization , 2017, ICLR.

[22]  Ilya Sutskever,et al.  Learning to Generate Reviews and Discovering Sentiment , 2017, ArXiv.

[23]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[24]  Min Sun,et al.  A Unified Model for Extractive and Abstractive Summarization using Inconsistency Loss , 2018, ACL.

[25]  Alexander M. Rush,et al.  Bottom-Up Abstractive Summarization , 2018, EMNLP.

[26]  Yen-Chun Chen,et al.  Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting , 2018, ACL.