TY - GEN
T1 - AIMAatSemEval-2024 Task 10: History-Based Emotion Recognition in Hindi-English Code-Mixed Conversations
AU - Abootorabi, Mohammad Mahdi
AU - Ghazizadeh, Nona
AU - Dalili, Seyed Arshan
AU - Kure, Alireza Ghahramani
AU - Dehghani, Mahshid
AU - Asgari, Ehsaneddin
PY - 2024/6
Y1 - 2024/6
N2 - In this study, we introduce a solution to the SemEval 2024 Task 10 on subtask 1, dedicated to Emotion Recognition in Conversation (ERC) in code-mixed Hindi-English conversations. ERC in code-mixed conversations presents unique challenges, as existing models are typically trained on monolingual datasets and may not perform well on code-mixed data. To address this, we propose a series of models that incorporate both the previous and future context of the current utterance, as well as the sequential information of the conversation. To facilitate the processing of code-mixed data, we developed a Hinglish-to-English translation pipeline to translate the code-mixed conversations into English. We designed four different base models, each utilizing powerful pre-trained encoders to extract features from the input but with varying architectures. By ensembling all of these models, we developed a final model that outperforms all other baselines.
AB - In this study, we introduce a solution to the SemEval 2024 Task 10 on subtask 1, dedicated to Emotion Recognition in Conversation (ERC) in code-mixed Hindi-English conversations. ERC in code-mixed conversations presents unique challenges, as existing models are typically trained on monolingual datasets and may not perform well on code-mixed data. To address this, we propose a series of models that incorporate both the previous and future context of the current utterance, as well as the sequential information of the conversation. To facilitate the processing of code-mixed data, we developed a Hinglish-to-English translation pipeline to translate the code-mixed conversations into English. We designed four different base models, each utilizing powerful pre-trained encoders to extract features from the input but with varying architectures. By ensembling all of these models, we developed a final model that outperforms all other baselines.
U2 - 10.18653/v1/2024.semeval-1.244
DO - 10.18653/v1/2024.semeval-1.244
M3 - Conference contribution
SP - 1704
EP - 1710
BT - Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
ER -