Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.17129 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911939742924800 |
|---|---|
| author | Cheng, Long Shao, Qihao Zhao, Christine Bi, Sheng Levow, Gina-Anne |
| author_facet | Cheng, Long Shao, Qihao Zhao, Christine Bi, Sheng Levow, Gina-Anne |
| contents | Cross-lingual emotion detection allows us to analyze global trends, public opinion, and social phenomena at scale. We participated in the Explainability of Cross-lingual Emotion Detection (EXALT) shared task, achieving an F1-score of 0.6046 on the evaluation set for the emotion detection sub-task. Our system outperformed the baseline by more than 0.16 F1-score absolute, and ranked second amongst competing systems. We conducted experiments using fine-tuning, zero-shot learning, and few-shot learning for Large Language Model (LLM)-based models as well as embedding-based BiLSTM and KNN for non-LLM-based techniques. Additionally, we introduced two novel methods: the Multi-Iteration Agentic Workflow and the Multi-Binary-Classifier Agentic Workflow. We found that LLM-based approaches provided good performance on multilingual emotion detection. Furthermore, ensembles combining all our experimented models yielded higher F1-scores than any single approach alone. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17129 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection Cheng, Long Shao, Qihao Zhao, Christine Bi, Sheng Levow, Gina-Anne Computation and Language Artificial Intelligence Cross-lingual emotion detection allows us to analyze global trends, public opinion, and social phenomena at scale. We participated in the Explainability of Cross-lingual Emotion Detection (EXALT) shared task, achieving an F1-score of 0.6046 on the evaluation set for the emotion detection sub-task. Our system outperformed the baseline by more than 0.16 F1-score absolute, and ranked second amongst competing systems. We conducted experiments using fine-tuning, zero-shot learning, and few-shot learning for Large Language Model (LLM)-based models as well as embedding-based BiLSTM and KNN for non-LLM-based techniques. Additionally, we introduced two novel methods: the Multi-Iteration Agentic Workflow and the Multi-Binary-Classifier Agentic Workflow. We found that LLM-based approaches provided good performance on multilingual emotion detection. Furthermore, ensembles combining all our experimented models yielded higher F1-scores than any single approach alone. |
| title | TEII: Think, Explain, Interact and Iterate with Large Language Models to Solve Cross-lingual Emotion Detection |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2405.17129 |