Loading...

AIMA at SemEval-2024 Task 3: Simple Yet Powerful Emotion Cause Pair Analysis

Kure, A.G ; Sharif University of Technology | 2024

187 Viewed
  1. Type of Document: Article
  2. Publisher: 2024
  3. Abstract:
  4. The SemEval-2024 Task 3 presents two subtasks focusing on emotion-cause pair extraction within conversational contexts. Subtask 1 revolves around the extraction of textual emotion-cause pairs, where causes are defined and annotated as textual spans within the conversation. Conversely, Subtask 2 extends the analysis to encompass multimodal cues, including language, audio, and vision, acknowledging instances where causes may not be exclusively represented in the textual data. Despite this, our model addresses Subtask 2 using the same architecture as Subtask 1, focusing solely on textual and linguistic cues. Our architecture is organized into three main segments: (i) embedding extraction, (ii) cause-pair extraction & emotion classification, and (iii) post-pair-extraction cause analysis using QA. Our approach, utilizing advanced techniques and task-specific fine-tuning, unravels complex conversational dynamics and identifies causality in emotions. Our team, AIMA (MotoMoto at the leaderboard), demonstrated strong performance in the SemEval-2024 Task 3 competition ranked as the 10th rank in subtask 1 and the 6th in subtask 2 out of 23 teams. The code for our model implementation is available on https://github.com/language-ml/SemEval2024-Task3. © 2024 Association for Computational Linguistics
  5. Keywords:
  6. Human computer interaction ; Modeling languages ; Causes analysis ; Embeddings ; Emotion classification ; Fine tuning ; Multimodal cues ; Pair analysis ; Performance ; Simple++ ; Subtask ; Textual data ; Computational linguistics
  7. Source: SemEval 2024 - 18th International Workshop on Semantic Evaluation, Proceedings of the Workshop ; 2024 , Pages 1698-1703 ; 979-889176107-0 (ISBN)
  8. URL: https://aclanthology.org/2024.semeval-1.243