Abstractive Multi-Document Summarization via Phrase Selection and Merging

TL;DR

This paper introduces a novel multi-document summarization method that constructs summaries by selecting and merging phrases, using optimization techniques to improve salience and linguistic quality, outperforming existing models on benchmark data.

Contribution

It presents a new abstraction-based framework that generates summaries through phrase-level selection and merging, optimizing for salience and coherence with integer linear programming.

Findings

Outperforms state-of-the-art models on TAC 2011 dataset

Achieves high scores on automated pyramid evaluation

Maintains good linguistic quality in generated summaries

Abstract

We propose an abstraction-based multi-document summarization framework that can construct new sentences by exploring more fine-grained syntactic units than sentences, namely, noun/verb phrases. Different from existing abstraction-based approaches, our method first constructs a pool of concepts and facts represented by phrases from the input documents. Then new sentences are generated by selecting and merging informative phrases to maximize the salience of phrases and meanwhile satisfy the sentence construction constraints. We employ integer linear optimization for conducting phrase selection and merging simultaneously in order to achieve the global optimal solution for a summary. Experimental results on the benchmark data set TAC 2011 show that our framework outperforms the state-of-the-art models under automated pyramid evaluation metric, and achieves reasonably well results on manual linguistic quality evaluation.