@inproceedings{qiu-etal-2024-joint,
title = "Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion",
author = "Qiu, Chenyu and
Qian, Pengjiang and
Wang, Chuang and
Yao, Jian and
Liu, Li and
Wei, Fang and
Eddie, Eddie",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.emnlp-main.851",
pages = "15257--15269",
abstract = "Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usage. In this paper, we propose Pre-Encoded Masked Language Model (PEMLM) to efficiently solve KGC problem. By encoding textual descriptions into semantic representations before training, the necessary resources are significantly reduced. Furthermore, we introduce a straightforward but effective fusion framework to integrate structural embedding with pre-encoded semantic description, which enhances the model{'}s prediction performance on 1-N relations. The experimental results demonstrate that our proposed strategy attains state-of-the-art performance on the WN18RR (MRR+5.4{\%} and Hits@1+6.4{\%}) and UMLS datasets. Compared to existing models, we have increased inference speed by 30x and reduced training memory by approximately 60{\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="qiu-etal-2024-joint">
<titleInfo>
<title>Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenyu</namePart>
<namePart type="family">Qiu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengjiang</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fang</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eddie</namePart>
<namePart type="family">Eddie</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>Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing</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>Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usage. In this paper, we propose Pre-Encoded Masked Language Model (PEMLM) to efficiently solve KGC problem. By encoding textual descriptions into semantic representations before training, the necessary resources are significantly reduced. Furthermore, we introduce a straightforward but effective fusion framework to integrate structural embedding with pre-encoded semantic description, which enhances the model’s prediction performance on 1-N relations. The experimental results demonstrate that our proposed strategy attains state-of-the-art performance on the WN18RR (MRR+5.4% and Hits@1+6.4%) and UMLS datasets. Compared to existing models, we have increased inference speed by 30x and reduced training memory by approximately 60%.</abstract>
<identifier type="citekey">qiu-etal-2024-joint</identifier>
<location>
<url>https://aclanthology.org/2024.emnlp-main.851</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>15257</start>
<end>15269</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion
%A Qiu, Chenyu
%A Qian, Pengjiang
%A Wang, Chuang
%A Yao, Jian
%A Liu, Li
%A Wei, Fang
%A Eddie, Eddie
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F qiu-etal-2024-joint
%X Knowledge graph completion (KGC) aims to infer missing or incomplete parts in knowledge graph. The existing models are generally divided into structure-based and description-based models, among description-based models often require longer training and inference times as well as increased memory usage. In this paper, we propose Pre-Encoded Masked Language Model (PEMLM) to efficiently solve KGC problem. By encoding textual descriptions into semantic representations before training, the necessary resources are significantly reduced. Furthermore, we introduce a straightforward but effective fusion framework to integrate structural embedding with pre-encoded semantic description, which enhances the model’s prediction performance on 1-N relations. The experimental results demonstrate that our proposed strategy attains state-of-the-art performance on the WN18RR (MRR+5.4% and Hits@1+6.4%) and UMLS datasets. Compared to existing models, we have increased inference speed by 30x and reduced training memory by approximately 60%.
%U https://aclanthology.org/2024.emnlp-main.851
%P 15257-15269
Markdown (Informal)
[Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion](https://aclanthology.org/2024.emnlp-main.851) (Qiu et al., EMNLP 2024)
ACL
- Chenyu Qiu, Pengjiang Qian, Chuang Wang, Jian Yao, Li Liu, Fang Wei, and Eddie Eddie. 2024. Joint Pre-Encoding Representation and Structure Embedding for Efficient and Low-Resource Knowledge Graph Completion. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 15257–15269, Miami, Florida, USA. Association for Computational Linguistics.