@inproceedings{-etal-2024-jmi,
    title = "{JMI} at {S}em{E}val 2024 Task 3: Two-step approach for multimodal {ECAC} using in-context learning with {GPT} and instruction-tuned Llama models",
    author = "Arefa  and
      Ansari, Mohammed Abbas  and
      Saxena, Chandni  and
      Ahmad, Tanvir",
    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/author-page-jing-li-nut/2024.semeval-1.223/",
    doi = "10.18653/v1/2024.semeval-1.223",
    pages = "1561--1576",
    abstract = "This paper presents our system development for SemEval-2024 Task 3: ``The Competition of Multimodal Emotion Cause Analysis in Conversations''. Effectively capturing emotions in human conversations requires integrating multiple modalities such as text, audio, and video. However, the complexities of these diverse modalities pose challenges for developing an efficient multimodal emotion cause analysis (ECA) system. Our proposed approach addresses these challenges by a two-step framework. We adopt two different approaches in our implementation. In Approach 1, we employ instruction-tuning with two separate Llama 2 models for emotion and cause prediction. In Approach 2, we use GPT-4V for conversation-level video description and employ in-context learning with annotated conversation using GPT 3.5. Our system wins rank 4, and system ablation experiments demonstrate that our proposed solutions achieve significant performance gains."
}