Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2302.10205 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914812117647360 |
|---|---|
| author | Wei, Xiang Cui, Xingyu Cheng, Ning Wang, Xiaobin Zhang, Xin Huang, Shen Xie, Pengjun Xu, Jinan Chen, Yufeng Zhang, Meishan Jiang, Yong Han, Wenjuan |
| author_facet | Wei, Xiang Cui, Xingyu Cheng, Ning Wang, Xiaobin Zhang, Xin Huang, Shen Xie, Pengjun Xu, Jinan Chen, Yufeng Zhang, Meishan Jiang, Yong Han, Wenjuan |
| contents | Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling takes. Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this work, we ask whether strong IE models can be constructed by directly prompting LLMs. Specifically, we transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE). With the power of ChatGPT, we extensively evaluate our framework on three IE tasks: entity-relation triple extract, named entity recognition, and event extraction. Empirical results on six datasets across two languages show that ChatIE achieves impressive performance and even surpasses some full-shot models on several datasets (e.g., NYT11-HRL). We believe that our work could shed light on building IE models with limited resources. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2302_10205 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT Wei, Xiang Cui, Xingyu Cheng, Ning Wang, Xiaobin Zhang, Xin Huang, Shen Xie, Pengjun Xu, Jinan Chen, Yufeng Zhang, Meishan Jiang, Yong Han, Wenjuan Computation and Language Zero-shot information extraction (IE) aims to build IE systems from the unannotated text. It is challenging due to involving little human intervention. Challenging but worthwhile, zero-shot IE reduces the time and effort that data labeling takes. Recent efforts on large language models (LLMs, e.g., GPT-3, ChatGPT) show promising performance on zero-shot settings, thus inspiring us to explore prompt-based methods. In this work, we ask whether strong IE models can be constructed by directly prompting LLMs. Specifically, we transform the zero-shot IE task into a multi-turn question-answering problem with a two-stage framework (ChatIE). With the power of ChatGPT, we extensively evaluate our framework on three IE tasks: entity-relation triple extract, named entity recognition, and event extraction. Empirical results on six datasets across two languages show that ChatIE achieves impressive performance and even surpasses some full-shot models on several datasets (e.g., NYT11-HRL). We believe that our work could shed light on building IE models with limited resources. |
| title | ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2302.10205 |