Entity commonsense representation for neural abstractive summarization

Reinald Kim Amplayo, Seonjae Lim, Seung Won Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

A major proportion of a text summary includes important entities found in the original text. These entities build up the topic of the summary. Moreover, they hold commonsense information once they are linked to a knowledge base. Based on these observations, this paper investigates the usage of linked entities to guide the decoder of a neural text summarizer to generate concise and better summaries. To this end, we leverage on an off-The-shelf entity linking system (ELS) to extract linked entities and propose Entity2Topic (E2T), a module easily attachable to a sequence-To-sequence model that transforms a list of entities into a vector representation of the topic of the summary. Current available ELS's are still not sufficiently effective, possibly introducing unresolved ambiguities and irrelevant entities. We resolve the imperfections of the ELS by (a) encoding entities with selective disambiguation, and (b) pooling entity vectors using firm attention. By applying E2T to a simple sequenceto-sequence model with attention mechanism as base model, we see significant improvements of the performance in the Gigaword (sentence to title) and CNN (long document to multi-sentence highlights) summarization datasets by at least 2 ROUGE points.

Original languageEnglish
Title of host publicationLong Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages697-707
Number of pages11
ISBN (Electronic)9781948087278
Publication statusPublished - 2018
Event2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States
Duration: 2018 Jun 12018 Jun 6

Publication series

NameNAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume1

Conference

Conference2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
CountryUnited States
CityNew Orleans
Period18/6/118/6/6

All Science Journal Classification (ASJC) codes

  • Linguistics and Language
  • Language and Linguistics
  • Computer Science Applications

Fingerprint Dive into the research topics of 'Entity commonsense representation for neural abstractive summarization'. Together they form a unique fingerprint.

  • Cite this

    Amplayo, R. K., Lim, S., & Hwang, S. W. (2018). Entity commonsense representation for neural abstractive summarization. In Long Papers (pp. 697-707). (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; Vol. 1). Association for Computational Linguistics (ACL).