A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection

Geng Tu, Ran Jing, Bin Liang, Min Yang, Kam-Fai Wong, Ruifeng Xu


Abstract
Unintended dataset biases typically exist in existing Emotion Recognition in Conversations (ERC) datasets, including label bias, where models favor the majority class due to imbalanced training data, as well as the speaker and neutral word bias, where models make unfair predictions because of excessive correlations between specific neutral words or speakers and classes. However, previous studies in ERC generally focus on capturing context-sensitive and speaker-sensitive dependencies, ignoring the unintended dataset biases of data, which hampers the generalization and fairness in ERC. To address this issue, we propose a Training-Free Debiasing framework (TFD) that operates during prediction without additional training. To ensure compatibility with various ERC models, it does not balance data or modify the model structure. Instead, TFD extracts biases from the model by generating counterfactual utterances and contexts and mitigates them using simple yet empirically robust element-wise subtraction operations. Extensive experiments on three public datasets demonstrate that TFD effectively improves generalization ability and fairness across different ERC models.
Anthology ID:
2023.emnlp-main.967
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15639–15650
Language:
URL:
https://aclanthology.org/2023.emnlp-main.967
DOI:
10.18653/v1/2023.emnlp-main.967
Bibkey:
Cite (ACL):
Geng Tu, Ran Jing, Bin Liang, Min Yang, Kam-Fai Wong, and Ruifeng Xu. 2023. A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 15639–15650, Singapore. Association for Computational Linguistics.
Cite (Informal):
A Training-Free Debiasing Framework with Counterfactual Reasoning for Conversational Emotion Detection (Tu et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2023.emnlp-main.967.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-4/2023.emnlp-main.967.mp4