Multi-level matching networks for text matching

Chunlin Xu, Zhiwei Lin, Shengli Wu, Hui Wang*

*Corresponding author for this work

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

2 Citations (Scopus)

Abstract

Text matching aims to establish the matching relationship between two texts. It is an important operation in some information retrieval related tasks such as question duplicate detection, question answering, and dialog systems. Bidirectional long short term memory (BiLSTM) coupled with attention mechanism has achieved state-of-the-art performance in text matching. A major limitation of existing works is that only high level contextualized word representations are utilized to obtain word level matching results without considering other levels of word representations, thus resulting in incorrect matching decisions for cases where two words with different meanings are very close in high level contextualized word representation space. Therefore, instead of making decisions utilizing single level word representations, a multi-level matching network (MMN) is proposed in this paper for text matching, which utilizes multiple levels of word representations to obtain multiple word level matching results for final text level matching decision. Experimental results on two widely used benchmarks, SNLI and Scaitail, show that the proposed MMN achieves the state-of-the-art performance.

Original languageEnglish
Title of host publicationSIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval
PublisherAssociation for Computing Machinery, Inc
Pages949-952
Number of pages4
ISBN (Electronic)9781450361729
DOIs
Publication statusPublished - 18 Jul 2019
Externally publishedYes
Event42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019 - Paris, France
Duration: 21 Jul 201925 Jul 2019

Publication series

NameSIGIR 2019 - Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

Conference

Conference42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2019
CountryFrance
CityParis
Period21/07/201925/07/2019

Bibliographical note

Funding Information:
This work is partially funded by the EU Horizon 2020 under Grant 690238 for DESIREE Project, under Grant 700381 for ASGARD project, by the UK EPSRC under Grant EP/P031668/1.

Publisher Copyright:
© 2019 Association for Computing Machinery.

Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.

Keywords

  • Attention
  • Multi-level matching network
  • Text matching

ASJC Scopus subject areas

  • Information Systems
  • Applied Mathematics
  • Software

Fingerprint Dive into the research topics of 'Multi-level matching networks for text matching'. Together they form a unique fingerprint.

Cite this