<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2021-global">
    <titleInfo>
        <title>Global entity alignment with Gated Latent Space Neighborhood Aggregation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Chen</namePart>
        <namePart type="family">Wei</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chen</namePart>
        <namePart type="family">Xiaoying</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiong</namePart>
        <namePart type="family">Shengwu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2021-aug</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">English</languageTerm>
        <languageTerm type="code" authority="iso639-2b">eng</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 20th Chinese National Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Chinese Information Processing Society of China</publisher>
            <place>
                <placeTerm type="text">Huhhot, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>“Existing entity alignment models mainly use the topology structure of the original knowledge graph and have achieved promising performance. However they are still challenged by the heterogeneous topological neighborhood structures which could cause the models to produce different representations of counterpart entities. In the paper we propose a global entity alignment model with gated latent space neighborhood aggregation (LatsEA) to address this challenge. Latent space neighborhood is formed by calculating the similarity between the entity embeddings it can introduce long-range neighbors to expand the topological neighborhood and reconcile the heterogeneous neighborhood structures. Meanwhile it uses vanilla GCN to aggregate the topological neighborhood and latent space neighborhood respectively. Then it uses an average gating mechanism to aggregate topological neighborhood information and latent space neighborhood information of the central entity. In order to further consider the interdependence between entity alignment decisions we propose a global entity alignment strategy i.e. formulate entity alignment as the maximum bipartite matching problem which is effectively solved by Hungarian algorithm. Our experiments with ablation studies on three real-world entity alignment datasets prove the effectiveness of the proposed model. Latent space neighborhood informationand global entity alignment decisions both contributes to the entity alignment performance improvement.”</abstract>
    <identifier type="citekey">wei-etal-2021-global</identifier>
    <location>
        <url>https://aclanthology.org/2021.ccl-1.102</url>
    </location>
    <part>
        <date>2021-aug</date>
        <extent unit="page">
            <start>1143</start>
            <end>1153</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Global entity alignment with Gated Latent Space Neighborhood Aggregation
%A Wei, Chen
%A Xiaoying, Chen
%A Shengwu, Xiong
%S Proceedings of the 20th Chinese National Conference on Computational Linguistics
%D 2021
%8 aug
%I Chinese Information Processing Society of China
%C Huhhot, China
%G English
%F wei-etal-2021-global
%X “Existing entity alignment models mainly use the topology structure of the original knowledge graph and have achieved promising performance. However they are still challenged by the heterogeneous topological neighborhood structures which could cause the models to produce different representations of counterpart entities. In the paper we propose a global entity alignment model with gated latent space neighborhood aggregation (LatsEA) to address this challenge. Latent space neighborhood is formed by calculating the similarity between the entity embeddings it can introduce long-range neighbors to expand the topological neighborhood and reconcile the heterogeneous neighborhood structures. Meanwhile it uses vanilla GCN to aggregate the topological neighborhood and latent space neighborhood respectively. Then it uses an average gating mechanism to aggregate topological neighborhood information and latent space neighborhood information of the central entity. In order to further consider the interdependence between entity alignment decisions we propose a global entity alignment strategy i.e. formulate entity alignment as the maximum bipartite matching problem which is effectively solved by Hungarian algorithm. Our experiments with ablation studies on three real-world entity alignment datasets prove the effectiveness of the proposed model. Latent space neighborhood informationand global entity alignment decisions both contributes to the entity alignment performance improvement.”
%U https://aclanthology.org/2021.ccl-1.102
%P 1143-1153

Markdown (Informal)

[Global entity alignment with Gated Latent Space Neighborhood Aggregation](https://aclanthology.org/2021.ccl-1.102) (Wei et al., CCL 2021)

• Global entity alignment with Gated Latent Space Neighborhood Aggregation (Wei et al., CCL 2021)

ACL

• Chen Wei, Chen Xiaoying, and Xiong Shengwu. 2021. Global entity alignment with Gated Latent Space Neighborhood Aggregation. In Proceedings of the 20th Chinese National Conference on Computational Linguistics, pages 1143–1153, Huhhot, China. Chinese Information Processing Society of China.