Emo-Gen BART - A Multitask Emotion-Informed Dialogue Generation Framework

Alok Debnath, Yvette Graham, Owen Conlan


Abstract
This paper is the model description for the Emo-Gen BART dialogue generation architecture, as submitted to the SCI-CHAT 2024 Shared Task. The Emotion-Informed Dialogue Generation model is a multi-task BARTbased model which performs dimensional and categorical emotion detection and uses that information to augment the input to the generation models. Our implementation is trained and validated against the IEMOCAP dataset, and compared against contemporary architectures in both dialogue emotion classification and dialogue generation. We show that certain loss function ablations are competitive against the state-of-the-art single-task models.
Anthology ID:
2024.scichat-1.7
Volume:
Proceedings of the 1st Workshop on Simulating Conversational Intelligence in Chat (SCI-CHAT 2024)
Month:
March
Year:
2024
Address:
St. Julians, Malta
Editors:
Yvette Graham, Qun Liu, Gerasimos Lampouras, Ignacio Iacobacci, Sinead Madden, Haider Khalid, Rameez Qureshi
Venues:
SCI-CHAT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
70–74
Language:
URL:
https://aclanthology.org/2024.scichat-1.7
DOI:
Bibkey:
Cite (ACL):
Alok Debnath, Yvette Graham, and Owen Conlan. 2024. Emo-Gen BART - A Multitask Emotion-Informed Dialogue Generation Framework. In Proceedings of the 1st Workshop on Simulating Conversational Intelligence in Chat (SCI-CHAT 2024), pages 70–74, St. Julians, Malta. Association for Computational Linguistics.
Cite (Informal):
Emo-Gen BART - A Multitask Emotion-Informed Dialogue Generation Framework (Debnath et al., SCI-CHAT-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.scichat-1.7.pdf