Work

A Survey on Open Information Extraction from Rule-based Model to Large Language Model

Year: 2022

Type: preprint

Abstract: Open Information Extraction (OpenIE) represents a crucial NLP task aimed at deriving structured information from unstructured text, unrestricted by relation type or domain. This survey paper provides an overview of OpenIE technologies spanning from 2007 to 2024, emphasizing a chronological perspective absent in prior surveys. It examines the evolution of task settings in OpenIE to align with the advances in recent technologies. The paper categorizes OpenIE approaches into rule-based, neural, and pre-trained large language models, discussing each within a chronological framework. Additionally, it highlights prevalent datasets and evaluation metrics currently in use. Building on this extensive review, the paper outlines potential future directions in terms of datasets, information sources, output formats, methodologies, and evaluation metrics.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2208.08690

Authors: Liu, Pai, Gao, Wenyang, Dong, Wenjie, Ai, Lin, Gong, Ziwei, Huang, Songfang, Li, Zongsheng, Hoque, Ehsan, Hirschberg, Julia, Zhang, Yue

Institutions: Westlake University, University of Rochester, Zhejiang University, Columbia University, Alibaba DAMO Academy (China), Northeastern University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: U.S. Department of Defense, Defense Advanced Research Projects Agency

OpenAlex ID: W4292419621

Cites:

Cited by: 1

Related to: 10