Multi-hop inference for question-driven summarization

• Main Authors: DENG, Yang, ZHANG, Wenxuan, LAM, Wai
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2020
• Subjects: Databases and Information Systems
• Online Access: https://ink.library.smu.edu.sg/sis_research/9154; https://ink.library.smu.edu.sg/context/sis_research/article/10157/viewcontent/2020.emnlp_main.547.pdf
• Institution: Singapore Management University

Question-driven summarization has been recently studied as an effective approach to summarizing the source document to produce concise but informative answers for non-factoid questions. In this work, we propose a novel question-driven abstractive summarization method, Multi-hop Selective Generator (MSG), to incorporate multi-hop reasoning into question-driven summarization and, meanwhile, provide justifications for the generated summaries. Specifically, we jointly model the relevance to the question and the interrelation among different sentences via a human-like multi-hop inference module, which captures important sentences for justifying the summarized answer. A gated selective pointer generator network with a multi-view coverage mechanism is designed to integrate diverse information from different perspectives. Experimental results show that the proposed method consistently outperforms state-of-the-art methods on two non-factoid QA datasets, namely WikiHow and PubMedQA.