References & Citations
Computer Science > Computation and Language
Title: A Survey on Open Information Extraction from Rule-based Model to Large Language Model
(Submitted on 18 Aug 2022 (v1), revised 16 Apr 2024 (this version, v2), latest version 10 May 2024 (v6))
Abstract: Open information extraction is an important NLP task that targets extracting structured information from unstructured text without limitations on the relation type or the domain of the text. This survey paper covers open information extraction technologies from 2007 to 2022 with a focus on new models not covered by previous surveys. We propose a new categorization method from the source of information perspective to accommodate the development of recent OIE technologies. In addition, we summarize three major approaches based on task settings as well as current popular datasets and model evaluation metrics. Given the comprehensive review, several future directions are shown from datasets, source of information, output form, method, and evaluation metric aspects.
Submission history
From: Pai Liu [view email][v1] Thu, 18 Aug 2022 08:03:45 GMT (425kb,D)
[v2] Tue, 16 Apr 2024 03:16:22 GMT (2072kb,D)
[v3] Thu, 18 Apr 2024 03:47:27 GMT (2072kb,D)
[v4] Fri, 26 Apr 2024 00:47:04 GMT (2072kb,D)
[v5] Tue, 30 Apr 2024 15:27:01 GMT (590kb,D)
[v6] Fri, 10 May 2024 16:33:47 GMT (2072kb,D)
Link back to: arXiv, form interface, contact.