Mitigating Linguistic Artifacts in Emotion Recognition for Conversations from TV Scripts to Daily Conversations

Page view(s)
9
Checked on Jul 19, 2024
Mitigating Linguistic Artifacts in Emotion Recognition for Conversations from TV Scripts to Daily Conversations
Title:
Mitigating Linguistic Artifacts in Emotion Recognition for Conversations from TV Scripts to Daily Conversations
Journal Title:
the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
DOI:
Keywords:
Publication Date:
21 May 2024
Citation:
Donovan Ong, Shuo Sun, Jian Su, and Bin Chen. 2024. Mitigating Linguistic Artifacts in Emotion Recognition for Conversations from TV Scripts to Daily Conversations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 11319–11324, Torino, Italia. ELRA and ICCL.
Abstract:
Emotion Recognition in Conversations (ERC) is a well-studied task with numerous potential real-world applications. However, existing ERC models trained on the MELD dataset derived from TV series, struggle when applied to daily conversation datasets. A closer examination of the datasets unveils the prevalence of linguistic artifacts such as repetitions and interjections in TV scripts, which ERC models may exploit when making predictions. To address this issue, we explore two techniques aimed at reducing the reliance of ERC models on these artifacts: 1) using contrastive learning to prioritize emotional features over dataset-specific linguistic style and 2) refining emotion predictions with pseudo-emotion intensity score. Our experiment results show that reducing reliance on the linguistic style found in TV transcripts could enhance model’s robustness and accuracy in diverse conversational contexts.
License type:
Attribution 4.0 International (CC BY 4.0)
Funding Info:
This research / project is supported by the National Research Foundation, Prime Minister’s Office - Campus for Research Excellence and Technological Enterprise (CREATE) programme
Grant Reference no. : NA
Description:
ISSN:
https://aclanthology.org/2024.lrec-main.989