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
Copyright Status
Unknown
Socpus ID
85119437074 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85119437074
STARS Citation
Song, Kaiqiang; Zhao, Lin; and Liu, Fei, "Structure-Infused Copy Mechanisms For Abstractive Summarization" (2018). Scopus Export 2015-2019. 9457.
https://stars.library.ucf.edu/scopus2015/9457