@inproceedings{niu-etal-2025-tree,
title = "Tree-{KG}: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains",
author = "Niu, Songjie and
Yang, Kaisen and
Zhao, Rui and
Liu, Yichao and
Li, Zonglin and
Wang, Hongning and
Chen, Wenguang",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-long.907/",
doi = "10.18653/v1/2025.acl-long.907",
pages = "18516--18529",
ISBN = "979-8-89176-251-0",
abstract = "In knowledge-intensive domains like scientific research, effective decisions rely on organizing and retrieving intricate data. Knowledge graphs (KGs) help by structuring entities, relations, and contextual dependencies, but building KGs in such domains is challenging due to inherent complexity, manual effort, and rapid evolution. Inspired by how humans organize knowledge hierarchically, we propose Tree-KG, an expandable framework that combines structured domain texts with advanced semantic techniques. First, Tree-KG builds a tree-like graph from textbook structures using large language models (LLMs) and domain-specific entities, creating an \textit{explicit KG}. Then, through iterative expansion with flexible, predefined operators, it uncovers \textit{hidden KG} while preserving semantic coherence. Experiments demonstrate that Tree-KG consistently surpasses competing methods, achieving the highest F1 scores (12{--}16{\%} above the second-best), with notable performance (F1 0.81) on the Text-Annotated dataset, highlighting its effectiveness in extracting high-quality information from source texts. Additionally, Tree-KG provides superior structural alignment, domain-specific extraction, and cost-efficiency, delivering robust results with reduced token usage and adaptable, resource-conscious deployment."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niu-etal-2025-tree">
<titleInfo>
<title>Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains</title>
</titleInfo>
<name type="personal">
<namePart type="given">Songjie</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaisen</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zonglin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongning</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenguang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-251-0</identifier>
</relatedItem>
<abstract>In knowledge-intensive domains like scientific research, effective decisions rely on organizing and retrieving intricate data. Knowledge graphs (KGs) help by structuring entities, relations, and contextual dependencies, but building KGs in such domains is challenging due to inherent complexity, manual effort, and rapid evolution. Inspired by how humans organize knowledge hierarchically, we propose Tree-KG, an expandable framework that combines structured domain texts with advanced semantic techniques. First, Tree-KG builds a tree-like graph from textbook structures using large language models (LLMs) and domain-specific entities, creating an explicit KG. Then, through iterative expansion with flexible, predefined operators, it uncovers hidden KG while preserving semantic coherence. Experiments demonstrate that Tree-KG consistently surpasses competing methods, achieving the highest F1 scores (12–16% above the second-best), with notable performance (F1 0.81) on the Text-Annotated dataset, highlighting its effectiveness in extracting high-quality information from source texts. Additionally, Tree-KG provides superior structural alignment, domain-specific extraction, and cost-efficiency, delivering robust results with reduced token usage and adaptable, resource-conscious deployment.</abstract>
<identifier type="citekey">niu-etal-2025-tree</identifier>
<identifier type="doi">10.18653/v1/2025.acl-long.907</identifier>
<location>
<url>https://aclanthology.org/2025.acl-long.907/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>18516</start>
<end>18529</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains
%A Niu, Songjie
%A Yang, Kaisen
%A Zhao, Rui
%A Liu, Yichao
%A Li, Zonglin
%A Wang, Hongning
%A Chen, Wenguang
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-251-0
%F niu-etal-2025-tree
%X In knowledge-intensive domains like scientific research, effective decisions rely on organizing and retrieving intricate data. Knowledge graphs (KGs) help by structuring entities, relations, and contextual dependencies, but building KGs in such domains is challenging due to inherent complexity, manual effort, and rapid evolution. Inspired by how humans organize knowledge hierarchically, we propose Tree-KG, an expandable framework that combines structured domain texts with advanced semantic techniques. First, Tree-KG builds a tree-like graph from textbook structures using large language models (LLMs) and domain-specific entities, creating an explicit KG. Then, through iterative expansion with flexible, predefined operators, it uncovers hidden KG while preserving semantic coherence. Experiments demonstrate that Tree-KG consistently surpasses competing methods, achieving the highest F1 scores (12–16% above the second-best), with notable performance (F1 0.81) on the Text-Annotated dataset, highlighting its effectiveness in extracting high-quality information from source texts. Additionally, Tree-KG provides superior structural alignment, domain-specific extraction, and cost-efficiency, delivering robust results with reduced token usage and adaptable, resource-conscious deployment.
%R 10.18653/v1/2025.acl-long.907
%U https://aclanthology.org/2025.acl-long.907/
%U https://doi.org/10.18653/v1/2025.acl-long.907
%P 18516-18529
Markdown (Informal)
[Tree-KG: An Expandable Knowledge Graph Construction Framework for Knowledge-intensive Domains](https://aclanthology.org/2025.acl-long.907/) (Niu et al., ACL 2025)
ACL