@inproceedings{rusnachenko-liang-2024-nicolay,
    title = "nicolay-r at {S}em{E}val-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States",
    author = "Rusnachenko, Nicolay  and
      Liang, Huizhi",
    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-1.4/",
    doi = "10.18653/v1/2024.semeval-1.4",
    pages = "22--27",
    abstract = "Emotion expression is one of the essential traits of conversations. It may be self-related or caused by another speaker. The variety of reasons may serve as a source of the further emotion causes: conversation history, speaker`s emotional state, etc. Inspired by the most recent advances in Chain-of-Thought, in this work, we exploit the existing three-hop reasoning approach (THOR) to perform large language model instruction-tuning for answering: emotion states (THOR-state), and emotion caused by one speaker to the other (THOR-cause). We equip THORcause with the reasoning revision (RR) for devising a reasoning path in fine-tuning. In particular, we rely on the annotated speaker emotion states to revise reasoning path. Our final submission, based on Flan-T5-base (250M) and the rule-based span correction technique, preliminary tuned with THOR-state and fine-tuned with THOR-cause-rr on competition training data, results in 3rd and 4th places (F1-proportional) and 5th place (F1-strict) among 15 participating teams. Our THOR implementation fork is publicly available: https://github.com/nicolay-r/THOR-ECAC"
}