Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912258069626880 |
|---|---|
| author | Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi |
| author_facet | Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi |
| contents | Developing a general-purpose extraction system that can extract events with massive types is a long-standing target in Event Extraction (EE). In doing so, the challenge comes from two aspects: 1) The absence of an efficient and effective annotation method. 2) The absence of a powerful extraction method can handle massive types. For the first challenge, we propose a collaborative annotation method based on Large Language Models (LLMs). Through collaboration among multiple LLMs, it first refines annotations of trigger words from distant supervision and then carries out argument annotation. Next, a voting phase consolidates the annotation preferences across different LLMs. Finally, we create the EEMT dataset, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types. For the second challenge, we propose an LLM-based Partitioning EE method called LLM-PEE. To overcome the limited context length of LLMs, LLM-PEE first recalls candidate event types and then splits them into multiple partitions for LLMs to extract events. The results in the supervised setting show that LLM-PEE outperforms the state-of-the-art methods by 5.4 in event detection and 6.1 in argument extraction. In the zero-shot setting, LLM-PEE achieves up to 12.9 improvement compared to mainstream LLMs, demonstrating its strong generalization capabilities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_02628 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction Liu, Wenxuan Li, Zixuan Bai, Long Zuo, Yuxin Xu, Daozhu Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi Computation and Language Artificial Intelligence Developing a general-purpose extraction system that can extract events with massive types is a long-standing target in Event Extraction (EE). In doing so, the challenge comes from two aspects: 1) The absence of an efficient and effective annotation method. 2) The absence of a powerful extraction method can handle massive types. For the first challenge, we propose a collaborative annotation method based on Large Language Models (LLMs). Through collaboration among multiple LLMs, it first refines annotations of trigger words from distant supervision and then carries out argument annotation. Next, a voting phase consolidates the annotation preferences across different LLMs. Finally, we create the EEMT dataset, the largest EE dataset to date, featuring over 200,000 samples, 3,465 event types, and 6,297 role types. For the second challenge, we propose an LLM-based Partitioning EE method called LLM-PEE. To overcome the limited context length of LLMs, LLM-PEE first recalls candidate event types and then splits them into multiple partitions for LLMs to extract events. The results in the supervised setting show that LLM-PEE outperforms the state-of-the-art methods by 5.4 in event detection and 6.1 in argument extraction. In the zero-shot setting, LLM-PEE achieves up to 12.9 improvement compared to mainstream LLMs, demonstrating its strong generalization capabilities. |
| title | Towards Event Extraction with Massive Types: LLM-based Collaborative Annotation and Partitioning Extraction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2503.02628 |