<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bollegala-etal-2021-relwalk">
    <titleInfo>
        <title>RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Danushka</namePart>
        <namePart type="family">Bollegala</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Huda</namePart>
        <namePart type="family">Hakami</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yuichi</namePart>
        <namePart type="family">Yoshida</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ken-ichi</namePart>
        <namePart type="family">Kawarabayashi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-04</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Paola</namePart>
            <namePart type="family">Merlo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jorg</namePart>
            <namePart type="family">Tiedemann</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Reut</namePart>
            <namePart type="family">Tsarfaty</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Embedding entities and relations of a knowledge graph in a low-dimensional space has shown impressive performance in predicting missing links between entities. Although progresses have been achieved, existing methods are heuristically motivated and theoretical understanding of such embeddings is comparatively underdeveloped. This paper extends the random walk model of word embeddings to Knowledge Graph Embeddings (KGEs) to derive a scoring function that evaluates the strength of a relation R between two entities h (head) and t (tail). Moreover, we show that marginal loss minimisation, a popular objective used in much prior work in KGE, follows naturally from the log-likelihood ratio maximisation under the probabilities estimated from the KGEs according to our theoretical relationship. We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph. Using the derived objective, accurate KGEs are learnt from FB15K237 and WN18RR benchmark datasets, providing empirical evidence in support of the theory.</abstract>
    <identifier type="citekey">bollegala-etal-2021-relwalk</identifier>
    <identifier type="doi">10.18653/v1/2021.eacl-main.133</identifier>
    <location>
        <url>https://aclanthology.org/2021.eacl-main.133</url>
    </location>
    <part>
        <date>2021-04</date>
        <extent unit="page">
            <start>1551</start>
            <end>1565</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding
%A Bollegala, Danushka
%A Hakami, Huda
%A Yoshida, Yuichi
%A Kawarabayashi, Ken-ichi
%Y Merlo, Paola
%Y Tiedemann, Jorg
%Y Tsarfaty, Reut
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F bollegala-etal-2021-relwalk
%X Embedding entities and relations of a knowledge graph in a low-dimensional space has shown impressive performance in predicting missing links between entities. Although progresses have been achieved, existing methods are heuristically motivated and theoretical understanding of such embeddings is comparatively underdeveloped. This paper extends the random walk model of word embeddings to Knowledge Graph Embeddings (KGEs) to derive a scoring function that evaluates the strength of a relation R between two entities h (head) and t (tail). Moreover, we show that marginal loss minimisation, a popular objective used in much prior work in KGE, follows naturally from the log-likelihood ratio maximisation under the probabilities estimated from the KGEs according to our theoretical relationship. We propose a learning objective motivated by the theoretical analysis to learn KGEs from a given knowledge graph. Using the derived objective, accurate KGEs are learnt from FB15K237 and WN18RR benchmark datasets, providing empirical evidence in support of the theory.
%R 10.18653/v1/2021.eacl-main.133
%U https://aclanthology.org/2021.eacl-main.133
%U https://doi.org/10.18653/v1/2021.eacl-main.133
%P 1551-1565

Markdown (Informal)

[RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding](https://aclanthology.org/2021.eacl-main.133) (Bollegala et al., EACL 2021)

• RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding (Bollegala et al., EACL 2021)

ACL

• Danushka Bollegala, Huda Hakami, Yuichi Yoshida, and Ken-ichi Kawarabayashi. 2021. RelWalk - A Latent Variable Model Approach to Knowledge Graph Embedding. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1551–1565, Online. Association for Computational Linguistics.