Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

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

TL;DR

This survey paper provides an overview of OpenIE technologies spanning from 2007 to 2024, emphasizing a chronological perspective absent in prior surveys, and outlines potential future directions in terms of datasets, information sources, output formats, methodologies, and evaluation metrics.

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.

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

TL;DR

This survey paper provides an overview of OpenIE technologies spanning from 2007 to 2024, emphasizing a chronological perspective absent in prior surveys, and outlines potential future directions in terms of datasets, information sources, output formats, methodologies, and evaluation metrics.

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.
Paper Structure (30 sections, 9 equations, 3 figures, 4 tables)

This paper contains 30 sections, 9 equations, 3 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Task Settings
  3. Datasets
  4. Evaluation
  5. A Chronological Review of Mainstream Methods
  6. Pre-neural Model Era
  7. Neural Model Era
  8. Large Language Models Era
  9. Discussion
  10. Co-Evolution of OpenIE: Task Settings and Model Capabilities
  11. Transforming OpenIE: The Impact of LLMs
  12. Future Directions
  13. Conclusion
  14. Open IE Methodologies in Details
  15. Open Relation Triplet Extraction
  16. ...and 15 more sections

Figures (3)

  • Figure 1: Comparison of OpenIE and standard relation extraction.
  • Figure 2: An overview of workflow processes in OpenIE task settings. ORTE aims to extract all n-ary relation tuples in the input, . ORSE finds relational spans according to previously extracted subjects and Objects. ORC pairs the input sentence with different subjects and objects within the sentence to form relation instances, relation instances are iteratively optimized in a supervised, unsupervised, or semi-supervised manner, and after the representations converge, clustering is performed. Objects of the same color indicate that they belong to the same relation cluster. To facilitate observation, we have bolded the borders of the three examples in the figure. Each circle represents the relation instances clustered into the same class by the clustering algorithm.
  • Figure 3: Chronological overview of Open IE methods.