Commonsense-Focused Dialogues for Response Generation: An Empirical Study

Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, Dilek Hakkani-Tur


Abstract
Smooth and effective communication requires the ability to perform latent or explicit commonsense inference. Prior commonsense reasoning benchmarks (such as SocialIQA and CommonsenseQA) mainly focus on the discriminative task of choosing the right answer from a set of candidates, and do not involve interactive language generation as in dialogue. Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet. In this paper, we present an empirical study of commonsense in dialogue response generation. We first auto-extract commonsensical dialogues from existing dialogue datasets by leveraging ConceptNet, a commonsense knowledge graph. Furthermore, building on social contexts/situations in SocialIQA, we collect a new dialogue dataset with 25K dialogues aimed at exhibiting social commonsense in an interactive setting. We evaluate response generation models trained using these datasets and find that models trained on both extracted and our collected data produce responses that consistently exhibit more commonsense than baselines. Finally we propose an approach for automatic evaluation of commonsense that relies on features derived from ConceptNet and pre-trained language and dialog models, and show reasonable correlation with human evaluation of responses’ commonsense quality.
Anthology ID:
2021.sigdial-1.13
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Editors:
Haizhou Li, Gina-Anne Levow, Zhou Yu, Chitralekha Gupta, Berrak Sisman, Siqi Cai, David Vandyke, Nina Dethlefs, Yan Wu, Junyi Jessy Li
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
121–132
Language:
URL:
https://aclanthology.org/2021.sigdial-1.13
DOI:
10.18653/v1/2021.sigdial-1.13
Bibkey:
Cite (ACL):
Pei Zhou, Karthik Gopalakrishnan, Behnam Hedayatnia, Seokhwan Kim, Jay Pujara, Xiang Ren, Yang Liu, and Dilek Hakkani-Tur. 2021. Commonsense-Focused Dialogues for Response Generation: An Empirical Study. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 121–132, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Commonsense-Focused Dialogues for Response Generation: An Empirical Study (Zhou et al., SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.13.pdf
Video:
 https://www.youtube.com/watch?v=dfYt0OfyTDA
Code
 alexa/commonsense-dialogues
Data
Commonsense-DialoguesATOMICDailyDialogFEDMuTual