Coarse-to-Fine Query Focused Multi-Document Summarization

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 3632–3645, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 3632 Coarse-to-Fine Query Focused Multi-Document Summarization Yumo Xu and Mirella Lapata Institute for Language, Cognition and Computation School of Informatics, University of Edinburgh 10 Crichton Street, Edinburgh EH8 9AB yumo.xu@ed.ac.uk, mlap@inf.ed.ac.uk Abstract We consider the problem of better modeling query-cluster interactions to facilitate query fo- cused multi-document summarization. Due to the lack of training data, existing work relies heavily on retrieval-style methods for assem- bling query relevant summaries. We propose a coarse-to-fine modeling framework which employs progressively more accurate modules for estimating whether text segments are rel- evant, likely to contain an answer, and cen- tral. The modules can be independently de- veloped and leverage training data if available. We present an instantiation of this framework with a trained evidence estimator which relies on distant supervision from question answer- ing (where various resources exist) to iden- tify segments which are likely to answer the query and should be included in the summary. Our framework1 is robust across domains and query types (i.e., long vs short) and outper- forms strong comparison systems on bench- mark datasets. 1 Introduction Query Focused Multi-Document Summarization (QFS; Dang 2006) aims to create a short summary from a set of documents that answers a specific query. It has various applications in personalized information retrieval and recommendation engines where search results can be tailored to an infor- mation need (e.g., a user might be looking for an overview summary or a more detailed one which would allow them to answer a specific question). Neural approaches have become increasingly popular in single-document text summarization (Nallapati et al., 2016; Paulus et al., 2018; Li et al., 2017b; See et al., 2017; Narayan et al., 2018; Gehrmann et al., 2018), thanks to the representa- tional power afforded by deeper architectures and the availability of large-scale datasets containing 1Our code can be downloaded from github.com/ yumoxu/querysum. hundreds of thousands of document-summary pairs (Sandhaus, 2008; Hermann et al., 2015; Grusky et al., 2018). Unfortunately, such datasets do not exist in QFS, and one might argue it is unrealistic they will ever be created for millions of queries, across different domains, and languages. In addi- tion to the difficulties in obtaining training data, another obstacle to the application of end-to-end neural models is the size and number of source doc- uments which can be very large. It is practically unfeasible (given memory limitations of current hardware) to train a model which encodes all of them into vectors and subsequently generates a summary from them. In this paper we propose a coarse-to-fine mod- eling framework for extractive QFS which incor- porates a relevance estimator for retrieving textual segments (e.g., sentences or longer passages) asso- ciated with a query, an evidence estimator which further isolates segments likely to contain answers to the query, and a centrality estimator which fi- nally selects which segments to include in the sum- mary. The vast majority of …

Content truncated to 500 words