@inproceedings{wang-etal-2024-phrases,
title = "When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language Models",
author = "Wang, Jiaxin and
Zhang, Lingling and
Lee, Wee Sun and
Zhong, Yujie and
Kang, Liwei and
Liu, Jun",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.acl-long.709",
pages = "13130--13147",
abstract = "Current clustering-based open relation extraction (OpenRE) methods usually apply clustering algorithms on top of pre-trained language models. However, this practice has three drawbacks. First, embeddings from language models are high-dimensional and anisotropic, so using simple metrics to calculate distances between these embeddings may not accurately reflect the relational similarity. Second, there exists a gap between the pre-trained language models and downstream clustering for their different objective forms. Third, clustering with embeddings deviates from the primary aim of relation extraction, as it does not directly obtain relations. In this work, we propose a new idea for OpenRE in the era of LLMs, that is, extracting relational phrases and directly exploiting the knowledge in LLMs to assess the semantic similarity between phrases without relying on any additional metrics. Based on this idea, we developed a framework, oreLLM, that makes two LLMs work collaboratively to achieve clustering and address the above issues. Experimental results on different datasets show that oreLLM outperforms current baselines by $1.4\%\sim 3.13\%$ in terms of clustering accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2024-phrases">
<titleInfo>
<title>When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingling</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wee</namePart>
<namePart type="given">Sun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yujie</namePart>
<namePart type="family">Zhong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liwei</namePart>
<namePart type="family">Kang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current clustering-based open relation extraction (OpenRE) methods usually apply clustering algorithms on top of pre-trained language models. However, this practice has three drawbacks. First, embeddings from language models are high-dimensional and anisotropic, so using simple metrics to calculate distances between these embeddings may not accurately reflect the relational similarity. Second, there exists a gap between the pre-trained language models and downstream clustering for their different objective forms. Third, clustering with embeddings deviates from the primary aim of relation extraction, as it does not directly obtain relations. In this work, we propose a new idea for OpenRE in the era of LLMs, that is, extracting relational phrases and directly exploiting the knowledge in LLMs to assess the semantic similarity between phrases without relying on any additional metrics. Based on this idea, we developed a framework, oreLLM, that makes two LLMs work collaboratively to achieve clustering and address the above issues. Experimental results on different datasets show that oreLLM outperforms current baselines by 1.4%\sim 3.13% in terms of clustering accuracy.</abstract>
<identifier type="citekey">wang-etal-2024-phrases</identifier>
<location>
<url>https://aclanthology.org/2024.acl-long.709</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13130</start>
<end>13147</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language Models
%A Wang, Jiaxin
%A Zhang, Lingling
%A Lee, Wee Sun
%A Zhong, Yujie
%A Kang, Liwei
%A Liu, Jun
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F wang-etal-2024-phrases
%X Current clustering-based open relation extraction (OpenRE) methods usually apply clustering algorithms on top of pre-trained language models. However, this practice has three drawbacks. First, embeddings from language models are high-dimensional and anisotropic, so using simple metrics to calculate distances between these embeddings may not accurately reflect the relational similarity. Second, there exists a gap between the pre-trained language models and downstream clustering for their different objective forms. Third, clustering with embeddings deviates from the primary aim of relation extraction, as it does not directly obtain relations. In this work, we propose a new idea for OpenRE in the era of LLMs, that is, extracting relational phrases and directly exploiting the knowledge in LLMs to assess the semantic similarity between phrases without relying on any additional metrics. Based on this idea, we developed a framework, oreLLM, that makes two LLMs work collaboratively to achieve clustering and address the above issues. Experimental results on different datasets show that oreLLM outperforms current baselines by 1.4%\sim 3.13% in terms of clustering accuracy.
%U https://aclanthology.org/2024.acl-long.709
%P 13130-13147
Markdown (Informal)
[When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language Models](https://aclanthology.org/2024.acl-long.709) (Wang et al., ACL 2024)
ACL