<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2016-gake">
    <titleInfo>
        <title>GAKE: Graph Aware Knowledge Embedding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Jun</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Minlie</namePart>
        <namePart type="family">Huang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiaoyan</namePart>
        <namePart type="family">Zhu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016-12</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Yuji</namePart>
            <namePart type="family">Matsumoto</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Rashmi</namePart>
            <namePart type="family">Prasad</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>The COLING 2016 Organizing Committee</publisher>
            <place>
                <placeTerm type="text">Osaka, Japan</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently. Most existing approaches treat the given knowledge base as a set of triplets, each of whose representation is then learned separately. However, as a fact, triples are connected and depend on each other. In this paper, we propose a graph aware knowledge embedding method (GAKE), which formulates knowledge base as a directed graph, and learns representations for any vertices or edges by leveraging the graph’s structural information. We introduce three types of graph context for embedding: neighbor context, path context, and edge context, each reflects properties of knowledge from different perspectives. We also design an attention mechanism to learn representative power of different vertices or edges. To validate our method, we conduct several experiments on two tasks. Experimental results suggest that our method outperforms several state-of-art knowledge embedding models.</abstract>
    <identifier type="citekey">feng-etal-2016-gake</identifier>
    <location>
        <url>https://aclanthology.org/C16-1062</url>
    </location>
    <part>
        <date>2016-12</date>
        <extent unit="page">
            <start>641</start>
            <end>651</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T GAKE: Graph Aware Knowledge Embedding
%A Feng, Jun
%A Huang, Minlie
%A Yang, Yang
%A Zhu, Xiaoyan
%Y Matsumoto, Yuji
%Y Prasad, Rashmi
%S Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F feng-etal-2016-gake
%X Knowledge embedding, which projects triples in a given knowledge base to d-dimensional vectors, has attracted considerable research efforts recently. Most existing approaches treat the given knowledge base as a set of triplets, each of whose representation is then learned separately. However, as a fact, triples are connected and depend on each other. In this paper, we propose a graph aware knowledge embedding method (GAKE), which formulates knowledge base as a directed graph, and learns representations for any vertices or edges by leveraging the graph’s structural information. We introduce three types of graph context for embedding: neighbor context, path context, and edge context, each reflects properties of knowledge from different perspectives. We also design an attention mechanism to learn representative power of different vertices or edges. To validate our method, we conduct several experiments on two tasks. Experimental results suggest that our method outperforms several state-of-art knowledge embedding models.
%U https://aclanthology.org/C16-1062
%P 641-651

Markdown (Informal)

[GAKE: Graph Aware Knowledge Embedding](https://aclanthology.org/C16-1062) (Feng et al., COLING 2016)

• GAKE: Graph Aware Knowledge Embedding (Feng et al., COLING 2016)

ACL

• Jun Feng, Minlie Huang, Yang Yang, and Xiaoyan Zhu. 2016. GAKE: Graph Aware Knowledge Embedding. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 641–651, Osaka, Japan. The COLING 2016 Organizing Committee.