@inproceedings{patel-etal-2024-iitk,
    title = "{IITK} at {S}em{E}val-2024 Task 10: Who is the speaker? Improving Emotion Recognition and Flip Reasoning in Conversations via Speaker Embeddings",
    author = "Patel, Shubham  and
      Shukla, Divyaksh  and
      Modi, Ashutosh",
    editor = {Ojha, Atul Kr.  and
      Do{\u{g}}ru{\"o}z, A. Seza  and
      Tayyar Madabushi, Harish  and
      Da San Martino, Giovanni  and
      Rosenthal, Sara  and
      Ros{\'a}, Aiala},
    booktitle = "Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.semeval-1.256/",
    doi = "10.18653/v1/2024.semeval-1.256",
    pages = "1811--1820",
    abstract = "This paper presents our approach for the SemEval-2024 Task 10: Emotion Discovery and Reasoning its Flip in Conversations. We propose a transformer-based speaker-centric model for the Emotion Flip Reasoning (EFR) task and a masked-memory network along with a speaker participation vector for the Emotion Recognition in Conversations (ERC) task. We propose a Probable Trigger Zone, which is more likely to contain the utterances causing the emotion of a speaker to flip. In EFR, sub-task 3, the proposed approach archives a 5.9 (F1 score) improvement over the provided task baseline. The ablation study results highlight the significance of various design choices in the proposed method."
}