nicolay-r at SemEval-2024 Task 3: Using Flan-T5 for Reasoning Emotion Cause in Conversations with Chain-of-Thought on Emotion States

Authors: Rusnachenko, N. and Liang, H.

Journal: Semeval 2024 18th International Workshop on Semantic Evaluation Proceedings of the Workshop

Pages: 22-27

DOI: 10.18653/v1/2024.semeval-1.4

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 (THORSTATE), and emotion caused by one speaker to the other (THORCAUSE). 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-T5base (250M) and the rule-based span correction technique, preliminary tuned with THORSTATE and fine-tuned with THORCAUSE-RR on competition training data, results in 3rd and 4th places (F1proportional) and 5th place (F1strict) among 15 participating teams. Our THOR implementation fork is publicly available: https://github.com/nicolay-r/THOR-ECAC.

Source: Scopus