Structure-Infused Copy Mechanisms For Abstractive Summarization

Abstract

Seq2seq learning has produced promising results on summarization. However, in many cases, system summaries still struggle to keep the meaning of the original intact. They may miss out important words or relations that play critical roles in the syntactic structure of source sentences. In this paper, we present structure-infused copy mechanisms to facilitate copying important words and relations from the source sentence to summary sentence. The approach naturally combines source dependency structure with the copy mechanism of an abstractive sentence summarizer. Experimental results demonstrate the effectiveness of incorporating source-side syntactic information in the system, and our proposed approach compares favorably to state-of-the-art methods.

Publication Date

1-1-2018

Publication Title

COLING 2018 - 27th International Conference on Computational Linguistics, Proceedings

Number of Pages

1717-1729

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

Socpus ID

85119437074 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85119437074

This document is currently not available here.

Share

COinS