nicolay-r at SemEval-2024 Task 3.1: Reasoning Emotion Cause Supported by Emotion State with Chain-of-Thoughts

Authors: Rusnachenko, N. and Liang, H.

Conference: The 18th International Workshop on Semantic Evaluation

Dates: 16-21 June 2024

DOI: 10.48550/arXiv.2404.03361

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 THOR-cause 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

https://eprints.bournemouth.ac.uk/39960/

Source: Manual

nicolay-r at SemEval-2024 Task 3.1: Reasoning Emotion Cause Supported by Emotion State with Chain-of-Thoughts

Authors: Rusnachenko, N. and Liang, H.

Conference: The 18th International Workshop on Semantic Evaluation

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 THOR-cause 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

https://eprints.bournemouth.ac.uk/39960/

https://semeval.github.io/SemEval2024/

Source: BURO EPrints