Abstract
Recent advancements in large language models have shown impressive performance in general chat. However, their domain-specific capabilities, particularly in information extraction, have certain limitations. Extracting structured information from natural language that deviates from known schemas or instructions has proven challenging for previous prompt-based methods. This motivated us to explore domain-specific modeling in chat-based language models as a solution for extracting structured information from natural language. In this paper, we present ChatUIE, an innovative unified information extraction framework built upon ChatGLM. Simultaneously, reinforcement learning is employed to improve and align various tasks that involve confusing and limited samples. Furthermore, we integrate generation constraints to address the issue of generating elements that are not present in the input. Our experimental results demonstrate that ChatUIE can significantly improve the performance of information extraction with a slight decrease in chatting ability.- Anthology ID:
- 2024.lrec-main.279
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 3146–3152
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.279
- DOI:
- Cite (ACL):
- Jun Xu, Mengshu Sun, Zhiqiang Zhang, and Jun Zhou. 2024. ChatUIE: Exploring Chat-based Unified Information Extraction Using Large Language Models. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3146–3152, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- ChatUIE: Exploring Chat-based Unified Information Extraction Using Large Language Models (Xu et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.279.pdf