Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/77337
Title: Improving semantic relevance for sequence-to-Sequence learning of Chinese social media text summarization
Authors: Ma, S
Sun, X
Xu, J
Wang, H
Li, W 
Su, Q
Issue Date: 2017
Publisher: Association for Computational Linguistics (ACL)
Source: ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), 30 Jul - 4 Aug 2017, v. 2, p. 635-640 How to cite?
Abstract: Current Chinese social media text summarization models are based on an encoder-decoder framework. Although its generated summaries are similar to source texts literally, they have low semantic relevance. In this work, our goal is to improve semantic relevance between source texts and summaries for Chinese social media summarization. We introduce a Semantic Relevance Based neural model to encourage high semantic similarity between texts and summaries. In our model, the source text is represented by a gated attention encoder, while the summary representation is produced by a decoder. Besides, the similarity score between the representations is maximized during training. Our experiments show that the proposed model outperforms baseline systems on a social media corpus.
URI: http://hdl.handle.net/10397/77337
ISBN: 9781945626760
DOI: 10.18653/v1/P17-2100
Appears in Collections:Conference Paper

Access
View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

54
Citations as of Aug 14, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.