TY - GEN
T1 - Improving semantic relevance for sequence-to-Sequence learning of Chinese social media text summarization
AU - Ma, Shuming
AU - Sun, Xu
AU - Xu, Jingjing
AU - Wang, Houfeng
AU - Li, Wenjie
AU - Su, Qi
PY - 2017/1/1
Y1 - 2017/1/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85040635086&partnerID=8YFLogxK
U2 - 10.18653/v1/P17-2100
DO - 10.18653/v1/P17-2100
M3 - Conference article published in proceeding or book
AN - SCOPUS:85040635086
T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
SP - 635
EP - 640
BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
PB - Association for Computational Linguistics (ACL)
T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Y2 - 30 July 2017 through 4 August 2017
ER -