Abstractive news summarization based on event semantic link network: 26th International Conference on Computational Linguistics

Wei Li, Lei He, Hai Zhuge

Research output: Other contribution

Abstract

This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation. Fine-grained event mentions and semantic relations between them are extracted to build a unified and connected event semantic link network, an abstract representation of source texts. A network reduction algorithm is proposed to summarize the most salient and coherent event information. New sentences with good linguistic quality are automatically generated and selected through sentences over-generation and greedy-selection processes. Experimental results on DUC2006 and DUC2007 datasets show that our system significantly outperforms the state-of-the-art extractive and abstractive baselines under both pyramid and ROUGE evaluation metrics.
Original languageEnglish
PublisherAssociation for Computational Linguistics
Number of pages11
ISBN (Print)978-4-87974-702-0
Publication statusPublished - 11 Dec 2016

Keywords

  • Summarization
  • sematnic link network
  • event

Fingerprint

Dive into the research topics of 'Abstractive news summarization based on event semantic link network: 26th International Conference on Computational Linguistics'. Together they form a unique fingerprint.

Cite this