Abstractive news summarization based on event semantic link network


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.

Divisions: College of Engineering & Physical Sciences
?? 50811700Jl ??
College of Engineering & Physical Sciences > Systems analytics research institute (SARI)
College of Engineering & Physical Sciences > Aston Institute of Materials Research (AIMR)
College of Engineering & Physical Sciences > Energy and Bioproducts Research Institute (EBRI)
Additional Information: This work is licenced under a Creative Commons Attribution 4.0 International License. License details: http:// creativecommons.org/licenses/by/4.0/
Event Title: 26th International Conference on Computational Linguistics
Event Type: Other
Event Dates: 2016-12-11 - 2016-12-16
Uncontrolled Keywords: Summarization,sematnic link network,event
ISBN: 978-4-87974-702-0
Last Modified: 08 Jul 2024 08:38
Date Deposited: 30 Jan 2018 09:45
PURE Output Type: Conference contribution
Published Date: 2016-12-11
Accepted Date: 2016-09-29
Authors: Li, Wei (ORCID Profile 0000-0003-4036-467X)
He, Lei
Zhuge, Hai (ORCID Profile 0000-0001-8250-6408)



Version: Accepted Version

License: Creative Commons Attribution

| Preview

Export / Share Citation


Additional statistics for this record