Reinforced Extractive Summarization with Question-Focused Rewards

We investigate a new training paradigm for extractive summarization. Traditionally, human abstracts are used to derive goldstandard labels for extraction units. However, the labels are often inaccurate, because human abstracts and source documents cannot be easily aligned at the word level. In this paper we convert human abstracts to a set of Cloze-style comprehension questions. System summaries are encouraged to preserve salient source content useful for answering questions and share common words with the abstracts. We use reinforcement learning to explore the space of possible extractive summaries and introduce a question-focused reward function to promote concise, fluent, and informative summaries. Our experiments show that the proposed method is effective. It surpasses state-of-the-art systems on the standard summarization dataset.

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

[2]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[3]  Alan Ritter,et al.  Adversarial Learning for Neural Dialogue Generation , 2017, EMNLP.

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

[5]  Daniel Marcu,et al.  Bayesian Query-Focused Summarization , 2006, ACL.

[6]  J. Steinberger,et al.  Using Latent Semantic Analysis in Text Summarization and Summary Evaluation , 2004 .

[7]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[8]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[9]  Matthew Richardson,et al.  MCTest: A Challenge Dataset for the Open-Domain Machine Comprehension of Text , 2013, EMNLP.

[10]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[11]  Benoit Favre,et al.  A Scalable Global Model for Summarization , 2009, ILP 2009.

[12]  Marc'Aurelio Ranzato,et al.  Sequence Level Training with Recurrent Neural Networks , 2015, ICLR.

[13]  Ani Nenkova,et al.  Beyond SumBasic: Task-focused summarization with sentence simplification and lexical expansion , 2007, Information Processing & Management.

[14]  Danqi Chen,et al.  A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task , 2016, ACL.

[15]  Mark T. Maybury,et al.  Automatic Summarization , 2002, Computational Linguistics.

[16]  Jason Weston,et al.  Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks , 2015, ICLR.

[17]  Fei Liu,et al.  Document Summarization via Guided Sentence Compression , 2013, EMNLP.

[18]  Bowen Zhou,et al.  Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond , 2016, CoNLL.

[19]  Nitish Srivastava,et al.  Improving Neural Networks with Dropout , 2013 .

[20]  Nathanael Chambers,et al.  A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories , 2016, NAACL.

[21]  Lin Zhao,et al.  Structure-Infused Copy Mechanisms for Abstractive Summarization , 2018, COLING.

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

[23]  Xiaojun Wan,et al.  Abstractive Document Summarization with a Graph-Based Attentional Neural Model , 2017, ACL.

[24]  Hoa Trang Dang,et al.  Overview of the TAC 2008 Update Summarization Task , 2008, TAC.

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

[26]  Mirella Lapata,et al.  Neural Summarization by Extracting Sentences and Words , 2016, ACL.

[27]  Jason Weston,et al.  A Neural Attention Model for Sentence Summarization , 2015 .

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

[29]  Eunsol Choi,et al.  Coarse-to-Fine Question Answering for Long Documents , 2016, ACL.

[30]  Tao Qin,et al.  Incorporating BERT into Neural Machine Translation , 2020, ICLR.

[31]  Zhen-Hua Ling,et al.  Distraction-Based Neural Networks for Document Summarization , 2016, ArXiv.

[32]  Regina Barzilay,et al.  Rationalizing Neural Predictions , 2016, EMNLP.

[33]  Furu Wei,et al.  Faithful to the Original: Fact Aware Neural Abstractive Summarization , 2017, AAAI.

[34]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[35]  U. Berkeley.  Exploring Content Models for Multi-Document Summarization , 2018 .

[36]  Mirella Lapata,et al.  Sentence Simplification with Deep Reinforcement Learning , 2017, EMNLP.

[37]  Dragomir R. Radev,et al.  LexRank: Graph-based Lexical Centrality as Salience in Text Summarization , 2004, J. Artif. Intell. Res..