Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection

Souvik Das, Sougata Saha, Rohini K. Srihari


Abstract
Personalized response selection systems are generally grounded on persona. However, a correlation exists between persona and empathy, which these systems do not explore well. Also, when a contradictory or off-topic response is selected, faithfulness to the conversation context plunges. This paper attempts to address these issues by proposing a suite of fusion strategies that capture the interaction between persona, emotion, and entailment information of the utterances. Ablation studies on the Persona-Chat dataset show that incorporating emotion and entailment improves the accuracy of response selection. We combine our fusion strategies and concept-flow encoding to train a BERT-based model which outperforms the previous methods by margins larger than 2.3% on original personas and 1.9% on revised personas in terms of hits@1 (top-1 accuracy), achieving a new state-of-the-art performance on the Persona-Chat dataset
Anthology ID:
2022.coling-1.44
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
532–541
Language:
URL:
https://aclanthology.org/2022.coling-1.44
DOI:
Bibkey:
Cite (ACL):
Souvik Das, Sougata Saha, and Rohini K. Srihari. 2022. Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection. In Proceedings of the 29th International Conference on Computational Linguistics, pages 532–541, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
Using Multi-Encoder Fusion Strategies to Improve Personalized Response Selection (Das et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.44.pdf