Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language units from multiple granularities (e.g., words, phrases, and sub-sentences, etc.); (2) local (e.g., a small window around a word) and long-range (e.g., words across the context and the response) dependencies may exist in dialogue data; and (3) the relationship between the context and the response candidate lies in multiple relevant semantic clues or relatively implicit semantic clues in some real cases. However, existing approaches usually encode the dialogue with mono-type representation and the interaction processes between the context and the response candidate are executed in a rather shallow manner, which may lead to an inadequate understanding of dialogue content and hinder the recognition of the semantic relevance between the context and response. To tackle these challenges, we propose a representation[K]-interaction[L]-matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection. Particularly, we construct different types of representations for utterance–response pairs and deepen them via alternate encoding and interaction. By this means, the model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair. Experiment results on three public benchmarks indicate that the proposed model significantly outperforms previous conventional context-response matching models and achieve slightly better results than the BERT model for multi-turn response selection in retrieval-based dialogue systems. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png ACM Transactions on Information Systems (TOIS) Association for Computing Machinery

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues

Download PDF
28 pages

Loading next page...
 
/lp/association-for-computing-machinery/response-ranking-with-multi-types-of-deep-interactive-representations-J46yhJPa7Z

References (67)

Publisher
Association for Computing Machinery
Copyright
Copyright © 2021 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ISSN
1046-8188
eISSN
1558-2868
DOI
10.1145/3462207
Publisher site
See Article on Publisher Site

Abstract

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language units from multiple granularities (e.g., words, phrases, and sub-sentences, etc.); (2) local (e.g., a small window around a word) and long-range (e.g., words across the context and the response) dependencies may exist in dialogue data; and (3) the relationship between the context and the response candidate lies in multiple relevant semantic clues or relatively implicit semantic clues in some real cases. However, existing approaches usually encode the dialogue with mono-type representation and the interaction processes between the context and the response candidate are executed in a rather shallow manner, which may lead to an inadequate understanding of dialogue content and hinder the recognition of the semantic relevance between the context and response. To tackle these challenges, we propose a representation[K]-interaction[L]-matching framework that explores multiple types of deep interactive representations to build context-response matching models for response selection. Particularly, we construct different types of representations for utterance–response pairs and deepen them via alternate encoding and interaction. By this means, the model can handle the relation of neighboring elements, phrasal pattern, and long-range dependencies during the representation and make a more accurate prediction through multiple layers of interactions between the context–response pair. Experiment results on three public benchmarks indicate that the proposed model significantly outperforms previous conventional context-response matching models and achieve slightly better results than the BERT model for multi-turn response selection in retrieval-based dialogue systems.

Journal

ACM Transactions on Information Systems (TOIS) – Association for Computing Machinery

Published: Aug 17, 2021

Keywords: Retrieval-based dialogue systems

There are no references for this article.