Neural abstractive summarization fusing by global generative topics

Yang Gao*, Yang Wang, Luyang Liu, Yidi Guo, Heyan Huang

*此作品的通讯作者

科研成果: 期刊稿件文章同行评审

15 引用 (Scopus)

摘要

Various efforts have been dedicated to automatically generate coherent, condensed and informative summaries.Most concentrate on improving the capability of generating neural language models locally, but do not consider global information. In real cases, a summary is comprehensively influenced by the full content of the source text and is especially guided by its core sense.To seamlessly integrate global semantic representation into a summarization generation system, we propose to incorporate a neural generative topic matrix as an abstractive level of topic information.By mapping global semantics into a local generative language model, the abstractive summarization is capable of generating succinct and recapitulative words or phrases. Extensive experiments on DUC-2004 and Gigaword datasets convincingly validate the proposed model.

源语言英语
页(从-至)5049-5058
页数10
期刊Neural Computing and Applications
32
9
DOI
出版状态已出版 - 1 5月 2020

指纹

探究 'Neural abstractive summarization fusing by global generative topics' 的科研主题。它们共同构成独一无二的指纹。

引用此

Gao, Y., Wang, Y., Liu, L., Guo, Y., & Huang, H. (2020). Neural abstractive summarization fusing by global generative topics. Neural Computing and Applications, 32(9), 5049-5058. https://doi.org/10.1007/s00521-018-3946-7