Neural response generation for customer service based on personality traits

Jonathan Herzig, Michal Shmueli-Scheuer, Tommy Sandbank, David Konopnicki

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

Abstract

We present a neural response generation model that generates responses conditioned on a target personality. The model learns high level features based on the target personality, and uses them to update its hidden state. Our model achieves performance improvements in both perplexity and BLEU scores over a baseline sequence-to-sequence model, and is validated by human judges.

Original languageEnglish
Title of host publicationINLG 2017 - 10th International Natural Language Generation Conference, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages252-256
Number of pages5
ISBN (Electronic)9781945626524
StatePublished - 2017
Externally publishedYes
Event10th International Natural Language Generation Conference, INLG 2017 - Santiago de Compostela, Spain
Duration: 4 Sep 20177 Sep 2017

Publication series

NameINLG 2017 - 10th International Natural Language Generation Conference, Proceedings of the Conference

Conference

Conference10th International Natural Language Generation Conference, INLG 2017
Country/TerritorySpain
CitySantiago de Compostela
Period4/09/177/09/17

Cite this