Guiding Extractive Summarization with Question-Answering Rewards

Proceedings of NAACL-HLT 2019, pages 2566–2577 Minneapolis, Minnesota, June 2 - June 7, 2019. c⃝2019 Association for Computational Linguistics 2566 Guiding Extractive Summarization with Question-Answering Rewards Kristjan Arumae and Fei Liu Computer Science Department University of Central Florida, Orlando, FL 32816, USA k.arumae@knights.ucf.edu feiliu@cs.ucf.edu Abstract Highlighting while reading is a natural behav- ior for people to track salient content of a doc- ument. It would be desirable to teach an ex- tractive summarizer to do the same. However, a major obstacle to the development of a super- vised summarizer is the lack of ground-truth. Manual annotation of extraction units is cost- prohibitive, whereas acquiring labels by auto- matically aligning human abstracts and source documents can yield inferior results. In this paper we describe a novel framework to guide a supervised, extractive summarization system with question-answering rewards. We argue that quality summaries should serve as a docu- ment surrogate to answer important questions, and such question-answer pairs can be conve- niently obtained from human abstracts. The system learns to promote summaries that are informative, fluent, and perform competitively on question-answering. Our results compare favorably with those reported by strong sum- marization baselines as evaluated by automatic metrics and human assessors. 1 Introduction Our increasingly digitized lifestyle calls for sum- marization techniques to produce short and accu- rate summaries that can be accessed at any time. These summaries should factually adhere to the content of the source text and present the reader with the key points therein. Although neural ab- stractive summarization has shown promising re- sults (Rush et al., 2015; Nallapati et al., 2016; See et al., 2017), these methods can have poten- tial drawbacks. It was revealed that abstracts gen- erated by neural systems sometimes alter or fal- sify objective details, and introduce new meanings not present in the original text (Cao et al., 2018). Reading these abstracts can lead to misinterpreta- tion of the source materials, which is clearly unde- sirable. In this work, we focus on extractive sum- marization, where the summaries are guaranteed (CNN) A judge this week sentenced a former TSA agent to six months in jail for secretly videotaping a female co-worker while she was in the bathroom, prosecutors said. During the investigation, detectives with the Metro Nashville Police Department in Tennessee also found that the agent, 33-year-old Daniel Boykin, entered the woman’s home multiple times, where he took videos, photos and other data. Police found more than 90 videos and 1,500 photos of the victim on Boykin’s phone and computer. The victim filed a complaint after seeing images of herself on his phone last year. [...] Comprehension Questions (Human Abstract): Former Daniel Boykin, 33, videotaped his female co-worker in the restroom, authorities say. Authorities say they found 90 videos and 1,500 photos of the victim on and computer. Table 1: An example extractive summary bolded in the arti- cle (top). Highlighted sections indicate salient segments use- ful for answering fill-in-the-blank questions generated from human abstracts (bottom). to remain faithful to the original content. Our …

Content truncated to 500 words