Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue

Tingchen Fu, Xueliang Zhao, Lemao Liu, Rui Yan


Abstract
Multi-turn response selection aims to retrieve a response for a dialogue context from a candidate pool and negative sampling is the key to its retrieval performance. However, previous methods of negative samples tend to yield false negatives due to the one-to-many property in open-domain dialogue, which is detrimental to the optimization process. To deal with the problem, we propose a sequential variational ladder auto-encoder to capture the diverse one-to-many transition pattern of multiple characteristics in open-domain dialogue. The learned transition logic thus assists in identifying potential positives in disguise. Meanwhile, we propose a TRIGGER framework to adjust negative sampling in the training process such that the scope of false negatives dynamically updates according to the model capacity. Extensive experiments on two benchmarks verify the effectiveness of our approach.
Anthology ID:
2023.findings-emnlp.513
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7650–7661
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.513
DOI:
10.18653/v1/2023.findings-emnlp.513
Bibkey:
Cite (ACL):
Tingchen Fu, Xueliang Zhao, Lemao Liu, and Rui Yan. 2023. Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 7650–7661, Singapore. Association for Computational Linguistics.
Cite (Informal):
Logic Unveils Truth, While Disguise Obscures It: Transition Logic Augmented Response Selection for Multi-Turn Dialogue (Fu et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.findings-emnlp.513.pdf