详解GPT-信息抽取任务 (GPT-3 FAMILY LARGE LANGUAGE MODELS)

GPT-3 FAMILY LARGE LANGUAGE MODELS

Information Extraction

自然语言处理信息提取任务（NLP-IE）：从非结构化文本数据中提取结构化数据，例如提取实体、关系和事件 [164]。将非结构化文本数据转换为结构化数据可以实现高效的数据处理、知识发现、决策制定并增强信息检索和搜索。

Information Extraction 子任务

信息抽取任务多种多样[153]：

1. 实体类型（entity typing）
2. 实体提取（entity extraction）
3. 关系分类（relation classification）
4. 关系提取（relation extraction）
5. 事件检测（event detection）
6. 事件参数提取（event argument extraction ）
7. 事件提取 （event extraction）

Entity typing (ET)：classifying identified named entity mentions into one of the predefined entity types [165].

Named Entity Recognition (NER)：identifying entity mentions and then assigning them to appropriate entity types [166].

Relation classification (RC)：identifying the semantic relationship between the given two target entities in a sentence [167].

Relation Extraction (RE)：extracting the entities and then classifying the semantic relationship between the two target entities, i.e., involves entity extraction followed by relation classification [168].

Event Detection (ED)：aims to identify and categorize words or phrases that trigger events [169].

Event Argument Extraction (EAE)：identifying event arguments, i.e., entities involved in the event and then classifying their roles [170].

Event Extraction (EE)：aims to extract both the events and the involved entities, i.e., it involves event detection followed by event argument extraction [171].

GPT relation classification 任务

[138], [149], [153]–[156], [163]

[138] Y. Wang, Y. Zhao, and L. Petzold, “Are large language models ready for healthcare? a comparative study on clinical language understanding,” arXiv preprint arXiv:2304.05368, 2023.  chain-of-thought (CoT)  self-question prompting (SQP)

链接：https://proceedings.mlr.press/v219/wang23c/wang23c.pdf

[149] B. J. Gutie ́rrez, N. McNeal, C. Washington, Y. Chen, L. Li, H. Sun, and Y. Su, “Thinking about gpt-3 in-context learning for biomedical ie? think again,” in Findings of the Association for Computational Linguistics: EMNLP 2022, 2022, pp. 4497–4512.

链接：https://arxiv.org/pdf/2203.08410

[153] B. Li, G. Fang, Y. Yang, Q. Wang, W. Ye, W. Zhao, and S. Zhang, “Evaluating chatgpt’s information extraction capabilities: An assessment of performance, explainability, calibration, and faithfulness,” arXiv preprint arXiv:2304.11633, 2023.  

链接：https://arxiv.org/pdf/2304.11633

[154] C. Chan, J. Cheng, W. Wang, Y. Jiang, T. Fang, X. Liu, and Y. Song, “Chatgpt evaluation on sentence level relations: A focus on temporal, causal, and discourse relations,” arXiv preprint arXiv:2304.14827, 2023.  

链接：https://arxiv.org/pdf/2304.14827

[155] X. Xu, Y. Zhu, X. Wang, and N. Zhang, “How to unleash the power of large language models for few-shot relation extraction?” arXiv preprint arXiv:2305.01555, 2023.  

链接：https://arxiv.org/pdf/2305.01555

[156] Z. Wan, F. Cheng, Z. Mao, Q. Liu, H. Song, J. Li, and S. Kurohashi, “Gpt-re: In-context learning for relation extraction using large language models,” arXiv preprint arXiv:2305.02105, 2023. chain-of-thought (CoT)

链接：https://arxiv.org/pdf/2305.02105

[163] K. Zhang, B. J. Gutie ́rrez, and Y. Su, “Aligning instruction tasks unlocks large language models as zero-shot relation extractors,” arXiv preprint arXiv:2305.11159, 2023.

链接：https://arxiv.org/pdf/2305.11159

GPT relation extraction 任务

[148], [151]–[153], [158], [161], [162],

[148] X. Wei, X. Cui, N. Cheng, X. Wang, X. Zhang, S. Huang, P. Xie, J. Xu, Y. Chen, M. Zhang et al., “Zero-shot information extraction via chatting with chatgpt,” arXiv preprint arXiv:2302.10205, 2023.

链接：https://eva.fing.edu.uy/pluginfile.php/524749/mod_folder/content/0/ChatIE_Zero-Shot%20Information%20Extraction%20via%20Chatting%20with%20ChatGPT.pdf

[151] H. Rehana, N. B. C ̧ am, M. Basmaci, Y. He, A.  ̈Ozgu ̈ r, and J. Hur, “Evaluation of gpt and bert-based models on identifying protein-protein interactions in biomedical text,” arXiv preprint arXiv:2303.17728, 2023.  

链接：https://pmc.ncbi.nlm.nih.gov/articles/PMC11101131/pdf/nihpp-2303.17728v2.pdf

[152] C. Yuan, Q. Xie, and S. Ananiadou, “Zero-shot temporal relation extraction with chatgpt,” arXiv preprint arXiv:2304.05454, 2023. chain-of-thought (CoT)  event ranking (ER)

链接：https://arxiv.org/pdf/2304.05454

[153] B. Li, G. Fang, Y. Yang, Q. Wang, W. Ye, W. Zhao, and S. Zhang, “Evaluating chatgpt’s information extraction capabilities: An assessment of performance, explainability, calibration, and faithfulness,” arXiv preprint arXiv:2304.11633, 2023.

链接：https://arxiv.org/pdf/2304.11633

[158] Y. Ma, Y. Cao, Y. Hong, and A. Sun, “Large language model is not a good few-shot information extractor, but a good reranker for hard samples!” arXiv preprint arXiv:2303.08559, 2023.

链接：https://arxiv.org/pdf/2303.08559

[161] S. Wadhwa, S. Amir, and B. C. Wallace, “Revisiting relation extraction in the era of large language models,” arXiv preprint arXiv:2305.05003, 2023. chain-of-thought (CoT)

链接：https://pmc.ncbi.nlm.nih.gov/articles/PMC10482322/pdf/nihms-1912166.pdf

[162] P. Li, T. Sun, Q. Tang, H. Yan, Y. Wu, X. Huang, and X. Qiu, “Codeie: Large code generation models are better few-shot information extractors,” arXiv preprint arXiv:2305.05711, 2023.

链接：https://arxiv.org/pdf/2305.05711

Summary

参考文献

[164] Y. Lu, Q. Liu, D. Dai, X. Xiao, H. Lin, X. Han, L. Sun, and H. Wu, “Unified structure generation for universal information extraction,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 5755–5772.

[165] Y. Chen, J. Cheng, H. Jiang, L. Liu, H. Zhang, S. Shi, and R. Xu, “Learning from sibling mentions with scalable graph inference in fine-grained entity typing,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 2076–2087.

[166] S. S. S. Das, A. Katiyar, R. J. Passonneau, and R. Zhang, “Container: Few-shot named entity recognition via contrastive learning,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 6338–6353.

[167] S. Wu and Y. He, “Enriching pre-trained language model with entity information for relation classification,” in Proceedings of the 28th ACM international conference on information and knowledge management, 2019, pp. 2361–2364.

[168] D. Ye, Y. Lin, P. Li, and M. Sun, “Packed levitated marker for entity and relation extraction,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 4904–4917.

[169] K. Zhao, X. Jin, L. Bai, J. Guo, and X. Cheng, “Knowledgeenhanced self-supervised prototypical network for few-shot event detection,” in Findings of the Association for Computational Linguistics: EMNLP 2022, 2022, pp. 6266–6275.  

[170] Y. Ma, Z. Wang, Y. Cao, M. Li, M. Chen, K. Wang, and J. Shao, “Prompt for extraction? paie: Prompting argument interaction for event argument extraction,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022, pp. 6759–6774.

[1] A Survey of GPT-3 Family Large Language  Models Including ChatGPT and GPT-4. 2023