In conclusion not repetition: Comprehensive abstractive summarization with diversified attention based on determinantal point processes

Lei Li, Wei Liu, Marina Litvak, Natalia Vanetik, Zuying Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

8 Scopus citations

Abstract

Various Seq2Seq learning models designed for machine translation were applied for abstractive summarization task recently. Despite these models provide high ROUGE scores, they are limited to generate comprehensive summaries with a high level of abstraction due to its degenerated attention distribution. We introduce Diverse Convolutional Seq2Seq Model(DivCNN Seq2Seq) using Determinan-tal Point Processes methods(Micro DPPs and Macro DPPs) to produce attention distribution considering both quality and diversity. Without breaking the end to end architecture, DivCNN Seq2Seq achieves a higher level of comprehensiveness compared to vanilla models and strong baselines. All the reproducible codes and datasets are available online.

Original languageEnglish
Title of host publicationCoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference
PublisherAssociation for Computational Linguistics
Pages822-832
Number of pages11
ISBN (Electronic)9781950737727
StatePublished - 1 Jan 2019
Externally publishedYes
Event23rd Conference on Computational Natural Language Learning, CoNLL 2019 - Hong Kong, China
Duration: 3 Nov 20194 Nov 2019

Publication series

NameCoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference

Conference

Conference23rd Conference on Computational Natural Language Learning, CoNLL 2019
Country/TerritoryChina
CityHong Kong
Period3/11/194/11/19

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Computational Theory and Mathematics

Fingerprint

Dive into the research topics of 'In conclusion not repetition: Comprehensive abstractive summarization with diversified attention based on determinantal point processes'. Together they form a unique fingerprint.

Cite this