Skip to main navigation Skip to search Skip to main content

TripleNet: Triple attention network for multi-turn response selection in retrieval-based chatbots

  • IFLYTEK Co., Ltd.
  • Harbin Institute of Technology

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

Abstract

We consider the importance of different utterances in the context for selecting the response usually depends on the current query.1 In this paper, we propose the model TripleNet to fully model the task with the triple (context, query, response) instead of (context, response) in previous works. The heart of TripeNet is a novel attention mechanism named triple attention to model the relationships within the triple at four levels. The new mechanism updates the representation for each element based on the attention with the other two concurrently and symmetrically. We match the triple (C, Q, R) centered on the response from char to context level for prediction. Experimental results on two large-scale multi-turn response selection datasets show that the proposed model can significantly outperform the state-of-the-art methods.

Original languageEnglish
Title of host publicationCoNLL 2019 - 23rd Conference on Computational Natural Language Learning, Proceedings of the Conference
PublisherAssociation for Computational Linguistics
Pages737-746
Number of pages10
ISBN (Electronic)9781950737727
DOIs
StatePublished - 2019
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

Fingerprint

Dive into the research topics of 'TripleNet: Triple attention network for multi-turn response selection in retrieval-based chatbots'. Together they form a unique fingerprint.

Cite this