@inproceedings{pai-etal-2024-survey,
title = "A Survey on Open Information Extraction from Rule-based Model to Large Language Model",
author = "Pai, Liu and
Gao, Wenyang and
Dong, Wenjie and
Ai, Lin and
Gong, Ziwei and
Huang, Songfang and
Zongsheng, Li and
Hoque, Ehsan and
Hirschberg, Julia and
Zhang, Yue",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.560/",
doi = "10.18653/v1/2024.findings-emnlp.560",
pages = "9586--9608",
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, this paper systematically reviews the evolution of task settings, data, evaluation metrics, and methodologies in the era of large language models, highlighting their mutual influence, comparing their capabilities, and examining their implications for open challenges and future research directions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pai-etal-2024-survey">
<titleInfo>
<title>A Survey on Open Information Extraction from Rule-based Model to Large Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Pai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Ai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziwei</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Songfang</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Zongsheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Hirschberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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, this paper systematically reviews the evolution of task settings, data, evaluation metrics, and methodologies in the era of large language models, highlighting their mutual influence, comparing their capabilities, and examining their implications for open challenges and future research directions.</abstract>
<identifier type="citekey">pai-etal-2024-survey</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.560</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.560/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>9586</start>
<end>9608</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Survey on Open Information Extraction from Rule-based Model to Large Language Model
%A Pai, Liu
%A Gao, Wenyang
%A Dong, Wenjie
%A Ai, Lin
%A Gong, Ziwei
%A Huang, Songfang
%A Zongsheng, Li
%A Hoque, Ehsan
%A Hirschberg, Julia
%A Zhang, Yue
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F pai-etal-2024-survey
%X 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, this paper systematically reviews the evolution of task settings, data, evaluation metrics, and methodologies in the era of large language models, highlighting their mutual influence, comparing their capabilities, and examining their implications for open challenges and future research directions.
%R 10.18653/v1/2024.findings-emnlp.560
%U https://aclanthology.org/2024.findings-emnlp.560/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.560
%P 9586-9608
Markdown (Informal)
[A Survey on Open Information Extraction from Rule-based Model to Large Language Model](https://aclanthology.org/2024.findings-emnlp.560/) (Pai et al., Findings 2024)
ACL
- Liu Pai, Wenyang Gao, Wenjie Dong, Lin Ai, Ziwei Gong, Songfang Huang, Li Zongsheng, Ehsan Hoque, Julia Hirschberg, and Yue Zhang. 2024. A Survey on Open Information Extraction from Rule-based Model to Large Language Model. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9586–9608, Miami, Florida, USA. Association for Computational Linguistics.