Reader-Aware Multi-Document Summarization via Sparse Coding

TL;DR

This paper introduces a reader-aware multi-document summarization method that incorporates reader comments and uses sparse coding to generate more salient and linguistically improved summaries, supported by a new dataset.

Contribution

It presents a novel RA-MDS framework combining reader comments with sparse coding and entity rewriting, along with a new dataset for evaluation.

Findings

Effective in generating salient summaries considering reader comments

Improves linguistic quality through entity rewriting

Demonstrates superior performance on new and classical datasets

Abstract

We propose a new MDS paradigm called reader-aware multi-document summarization (RA-MDS). Specifically, a set of reader comments associated with the news reports are also collected. The generated summaries from the reports for the event should be salient according to not only the reports but also the reader comments. To tackle this RA-MDS problem, we propose a sparse-coding-based method that is able to calculate the salience of the text units by jointly considering news reports and reader comments. Another reader-aware characteristic of our framework is to improve linguistic quality via entity rewriting. The rewriting consideration is jointly assessed together with other summarization requirements under a unified optimization model. To support the generation of compressive summaries via optimization, we explore a finer syntactic unit, namely, noun/verb phrase. In this work, we also generate a data set for conducting RA-MDS. Extensive experiments on this data set and some classical data sets demonstrate the effectiveness of our proposed approach.