Abstractive Multi-Document Summarization via Phrase Selection and Merging

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.

11 pages, 1 figure, accepted as a full paper at ACL 2015

References in corpus (2)

• Learning Mixtures of Submodular Shells with Application to Document Summarization
• Modelling, Visualising and Summarising Documents with a Single Convolutional Neural Network

Cited by in corpus (8)

• Neural Rating Regression with Abstractive Tips Generation for Recommendation
• Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting
• Neural Network-Based Abstract Generation for Opinions and Arguments
• Adapting the Neural Encoder-Decoder Framework from Single to Multi-Document Summarization
• DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization
• Unsupervised Summarization by Jointly Extracting Sentences and Keywords
• Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
• Enumeration of Extractive Oracle Summaries