N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models

Shiki Sato, Reina Akama, Hiroki Ouchi, Ryoko Tokuhisa, Jun Suzuki, Kentaro Inui


Abstract
Avoiding the generation of responses that contradict the preceding context is a significant challenge in dialogue response generation. One feasible method is post-processing, such as filtering out contradicting responses from a resulting n-best response list. In this scenario, the quality of the n-best list considerably affects the occurrence of contradictions because the final response is chosen from this n-best list. This study quantitatively analyzes the contextual contradiction-awareness of neural response generation models using the consistency of the n-best lists. Particularly, we used polar questions as stimulus inputs for concise and quantitative analyses. Our tests illustrate the contradiction-awareness of recent neural response generation models and methodologies, followed by a discussion of their properties and limitations.
Anthology ID:
2022.sigdial-1.60
Volume:
Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2022
Address:
Edinburgh, UK
Editors:
Oliver Lemon, Dilek Hakkani-Tur, Junyi Jessy Li, Arash Ashrafzadeh, Daniel Hernández Garcia, Malihe Alikhani, David Vandyke, Ondřej Dušek
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
637–644
Language:
URL:
https://aclanthology.org/2022.sigdial-1.60
DOI:
10.18653/v1/2022.sigdial-1.60
Bibkey:
Cite (ACL):
Shiki Sato, Reina Akama, Hiroki Ouchi, Ryoko Tokuhisa, Jun Suzuki, and Kentaro Inui. 2022. N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models. In Proceedings of the 23rd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 637–644, Edinburgh, UK. Association for Computational Linguistics.
Cite (Informal):
N-best Response-based Analysis of Contradiction-awareness in Neural Response Generation Models (Sato et al., SIGDIAL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigdial-1.60.pdf
Code
 shiki-sato/nbest-contradiction-analysis