An Entity-Driven Framework for Abstractive Summarization

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 3280–3291, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 3280 An Entity-Driven Framework for Abstractive Summarization Eva Sharma1* Luyang Huang2* Zhe Hu1* and Lu Wang1 1Khoury College of Computer Sciences, Northeastern University, Boston, MA 02115 2Department of Electrical and Computer Engineering, Boston University, Boston, MA 02215 1evasharma@ccs.neu.edu, hu.zhe@husky.neu.edu, luwang@ccs.neu.edu 2lyhuang@bu.edu Abstract Abstractive summarization systems aim to produce more coherent and concise summaries than their extractive counterparts. Popular neural models have achieved impressive re- sults for single-document summarization, yet their outputs are often incoherent and unfaith- ful to the input. In this paper, we intro- duce SENECA, a novel System for ENtity- drivEn Coherent Abstractive summarization framework that leverages entity information to generate informative and coherent abstracts. Our framework takes a two-step approach: (1) an entity-aware content selection module first identifies salient sentences from the in- put, then (2) an abstract generation module conducts cross-sentence information compres- sion and abstraction to generate the final sum- mary, which is trained with rewards to pro- mote coherence, conciseness, and clarity. The two components are further connected using reinforcement learning. Automatic evalua- tion shows that our model significantly out- performs previous state-of-the-art on ROUGE and our proposed coherence measures on New York Times and CNN/Daily Mail datasets. Human judges further rate our system sum- maries as more informative and coherent than those by popular summarization models. 1 Introduction Automatic abstractive summarization carries strong promise for producing concise and co- herent summaries to facilitate quick information consumption (Luhn, 1958). Recent progress in neural abstractive summarization has shown end- to-end trained models (Nallapati et al., 2016; Tan et al., 2017a; Celikyilmaz et al., 2018; Kry´sci´nski et al., 2018) excelling at producing fluent sum- maries. Though encouraging, their outputs are * These authors contributed equally. Work done while LH was at Northeastern University. Input Article: . . . Prime Minister Bertie Ahern of Ireland called Sunday for a general election on May 24. [Mr. Ahern] and his centrist party have governed in a coali- tion government since 1197 . . . Under Irish law, which requires legislative elections every five years, Mr. Ahern had to call elections by midsummer. On Sunday, {he} said he would base his campaign for re- election on his work to strengthen the economy and ef- forts to revive Northern Ireland’s stalled peace process this year. Political analysts said they expected Mr. Ahern ’s work in Northern Ireland to be an asset . . . Human Summary: 1 Prime Min Bertie Ahern of Ireland calls for general election on May 24. 2 [He] is required by law to call elections by midsummer. 3 Opinion polls suggest his centrist government is in dan- ger of losing its majority in Parliament because of public disgruntlement about overburdened public services. 4 {Ahern} says he would base his campaign for re- election on his work to strengthen economy and his efforts …

Content truncated to 500 words