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

TL;DR

This survey comprehensively reviews the evolution of Open Information Extraction from rule-based methods to large language models, highlighting technological progress, datasets, and future research directions in this NLP field.

Contribution

It provides a chronological overview of OpenIE approaches from 2007 to 2024, categorizing methods and discussing advancements, datasets, and evaluation metrics, which was lacking in prior surveys.

Findings

Categorization of OpenIE approaches into rule-based, neural, and large language models

Analysis of datasets and evaluation metrics used in OpenIE research

Identification of future directions for datasets, methodologies, and evaluation

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.