@inproceedings{wang-etal-2024-true,
title = "{TRUE}-{UIE}: Two Universal Relations Unify Information Extraction Tasks",
author = "Wang, Yucheng and
Yu, Bowen and
Liu, Yilin and
Lu, Shudong",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.103",
pages = "1863--1876",
abstract = "Information extraction (IE) encounters challenges due to the variety of schemas and objectives that differ across tasks. Recent advancements hint at the potential for universal approaches to model such tasks, referred to as Universal Information Extraction (UIE). While handling diverse tasks in one model, their generalization is limited since they are actually learning task-specific knowledge.In this study, we introduce an innovative paradigm known as TRUE-UIE, wherein all IE tasks are aligned to learn the same goals: extracting mention spans and two universal relations named $\mathtt{NEXT}$ and $\mathtt{IS}$. During the decoding process, the $\mathtt{NEXT}$ relation is utilized to group related elements, while the $\mathtt{IS}$ relation, in conjunction with structured language prompts, undertakes the role of type recognition. Additionally, we consider the sequential dependency of tokens during span extraction, an aspect often overlooked in prevalent models.Our empirical experiments indicate that TRUE-UIE achieves state-of-the-art performance on established benchmarks encompassing 16 datasets, spanning 7 diverse IE tasks. Further evaluations reveal that our approach effectively share knowledge between different IE tasks, showcasing significant transferability in zero-shot and few-shot scenarios.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-true">
<titleInfo>
<title>TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yucheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bowen</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yilin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shudong</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information extraction (IE) encounters challenges due to the variety of schemas and objectives that differ across tasks. Recent advancements hint at the potential for universal approaches to model such tasks, referred to as Universal Information Extraction (UIE). While handling diverse tasks in one model, their generalization is limited since they are actually learning task-specific knowledge.In this study, we introduce an innovative paradigm known as TRUE-UIE, wherein all IE tasks are aligned to learn the same goals: extracting mention spans and two universal relations named \mathttNEXT and \mathttIS. During the decoding process, the \mathttNEXT relation is utilized to group related elements, while the \mathttIS relation, in conjunction with structured language prompts, undertakes the role of type recognition. Additionally, we consider the sequential dependency of tokens during span extraction, an aspect often overlooked in prevalent models.Our empirical experiments indicate that TRUE-UIE achieves state-of-the-art performance on established benchmarks encompassing 16 datasets, spanning 7 diverse IE tasks. Further evaluations reveal that our approach effectively share knowledge between different IE tasks, showcasing significant transferability in zero-shot and few-shot scenarios.</abstract>
<identifier type="citekey">wang-etal-2024-true</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.103</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>1863</start>
<end>1876</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks
%A Wang, Yucheng
%A Yu, Bowen
%A Liu, Yilin
%A Lu, Shudong
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wang-etal-2024-true
%X Information extraction (IE) encounters challenges due to the variety of schemas and objectives that differ across tasks. Recent advancements hint at the potential for universal approaches to model such tasks, referred to as Universal Information Extraction (UIE). While handling diverse tasks in one model, their generalization is limited since they are actually learning task-specific knowledge.In this study, we introduce an innovative paradigm known as TRUE-UIE, wherein all IE tasks are aligned to learn the same goals: extracting mention spans and two universal relations named \mathttNEXT and \mathttIS. During the decoding process, the \mathttNEXT relation is utilized to group related elements, while the \mathttIS relation, in conjunction with structured language prompts, undertakes the role of type recognition. Additionally, we consider the sequential dependency of tokens during span extraction, an aspect often overlooked in prevalent models.Our empirical experiments indicate that TRUE-UIE achieves state-of-the-art performance on established benchmarks encompassing 16 datasets, spanning 7 diverse IE tasks. Further evaluations reveal that our approach effectively share knowledge between different IE tasks, showcasing significant transferability in zero-shot and few-shot scenarios.
%U https://aclanthology.org/2024.naacl-long.103
%P 1863-1876
Markdown (Informal)
[TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks](https://aclanthology.org/2024.naacl-long.103) (Wang et al., NAACL 2024)
ACL
- Yucheng Wang, Bowen Yu, Yilin Liu, and Shudong Lu. 2024. TRUE-UIE: Two Universal Relations Unify Information Extraction Tasks. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 1863–1876, Mexico City, Mexico. Association for Computational Linguistics.