<?xml version="1.0" encoding="ISO-8859-1"?><article xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<front>
<journal-meta>
<journal-id>1405-5546</journal-id>
<journal-title><![CDATA[Computación y Sistemas]]></journal-title>
<abbrev-journal-title><![CDATA[Comp. y Sist.]]></abbrev-journal-title>
<issn>1405-5546</issn>
<publisher>
<publisher-name><![CDATA[Instituto Politécnico Nacional, Centro de Investigación en Computación]]></publisher-name>
</publisher>
</journal-meta>
<article-meta>
<article-id>S1405-55462016000300459</article-id>
<article-id pub-id-type="doi">10.13053/cys-20-3-2472</article-id>
<title-group>
<article-title xml:lang="en"><![CDATA[A Novel Multimodal Deep Neural Network Framework for Extending Knowledge Base]]></article-title>
</title-group>
<contrib-group>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Yu]]></surname>
<given-names><![CDATA[Zhao]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Sheng]]></surname>
<given-names><![CDATA[Gao]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Gallinari]]></surname>
<given-names><![CDATA[Patrick]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
<contrib contrib-type="author">
<name>
<surname><![CDATA[Jun]]></surname>
<given-names><![CDATA[Guo]]></given-names>
</name>
<xref ref-type="aff" rid="Aff"/>
</contrib>
</contrib-group>
<aff id="Af1">
<institution><![CDATA[,Beijing University of Posts and Telecommunications  ]]></institution>
<addr-line><![CDATA[Beijing ]]></addr-line>
<country>China</country>
</aff>
<aff id="Af2">
<institution><![CDATA[,Universite Pierre et Marie Curie  ]]></institution>
<addr-line><![CDATA[Paris ]]></addr-line>
<country>France</country>
</aff>
<pub-date pub-type="pub">
<day>00</day>
<month>09</month>
<year>2016</year>
</pub-date>
<pub-date pub-type="epub">
<day>00</day>
<month>09</month>
<year>2016</year>
</pub-date>
<volume>20</volume>
<numero>3</numero>
<fpage>459</fpage>
<lpage>466</lpage>
<copyright-statement/>
<copyright-year/>
<self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_arttext&amp;pid=S1405-55462016000300459&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_abstract&amp;pid=S1405-55462016000300459&amp;lng=en&amp;nrm=iso"></self-uri><self-uri xlink:href="http://www.scielo.org.mx/scielo.php?script=sci_pdf&amp;pid=S1405-55462016000300459&amp;lng=en&amp;nrm=iso"></self-uri><abstract abstract-type="short" xml:lang="en"><p><![CDATA[Abstract Knowledge base is a very important database for knowledge management, which is very useful for Question Answering, Query Expansion and other AI tasks. However, due to the fast-growing knowledge on the web and not all common knowledge expressed in the text is explicit, the knowledge base always suffers from incompleteness. Recently many researchers are trying to solve the problem as link prediction, only using the existing knowledge base, however, it is just knowledge base completion without adding new entities, which emerges from unstructured text not in existing knowledge base. In this paper, we propose a multimodal deep neural network framework that trying to learn new entities from unstructured text and to extend the knowledge base. Experiments demonstrate the excellent performance.]]></p></abstract>
<kwd-group>
<kwd lng="en"><![CDATA[Extending knowledge base]]></kwd>
<kwd lng="en"><![CDATA[deep neural network]]></kwd>
<kwd lng="en"><![CDATA[word embedding]]></kwd>
<kwd lng="en"><![CDATA[embedding-based model]]></kwd>
</kwd-group>
</article-meta>
</front><back>
<ref-list>
<ref id="B1">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bollacker]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Evans]]></surname>
<given-names><![CDATA[C.]]></given-names>
</name>
<name>
<surname><![CDATA[Paritosh]]></surname>
<given-names><![CDATA[P.]]></given-names>
</name>
<name>
<surname><![CDATA[Sturge]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Taylor]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Freebase: a collaboratively created graph database for structuring human knowledge]]></source>
<year>2008</year>
<conf-name><![CDATA[ Proceedings of the 2008th ACM SIGMOD]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B2">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[A semantic matching energy function for learning with multi-relational data]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bordes]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Glorot]]></surname>
<given-names><![CDATA[X.]]></given-names>
</name>
<name>
<surname><![CDATA[Weston]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Machine Learning]]></source>
<year>2013</year>
<publisher-name><![CDATA[Machine Learning]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B3">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bordes]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Usunier]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Garcia-Duran]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Weston]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Yakhnenko]]></surname>
<given-names><![CDATA[O.]]></given-names>
</name>
</person-group>
<source><![CDATA[Translating embeddings for modeling multi-relational]]></source>
<year>2013</year>
<conf-name><![CDATA[ Proceedings of Neural Information Processing Systems]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B4">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Bordes]]></surname>
<given-names><![CDATA[A.]]></given-names>
</name>
<name>
<surname><![CDATA[Weston]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[Collobert]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Bengio]]></surname>
<given-names><![CDATA[Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning structured embeddings of knowledge bases]]></source>
<year>2011</year>
<conf-name><![CDATA[ 25th Annual Conference on Artificial Intelligence]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B5">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Collobert]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Weston]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[A unified architecture for natural language processing: Deep neural networks with multitask learning]]></source>
<year>2008</year>
<conf-name><![CDATA[ 25th international conference on Machine learning]]></conf-name>
<conf-loc> </conf-loc>
<page-range>160-7</page-range></nlm-citation>
</ref>
<ref id="B6">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Natural language processing (almost) from scratch]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Collobert]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Weston]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
<name>
<surname><![CDATA[L.]]></surname>
<given-names><![CDATA[B.]]></given-names>
</name>
</person-group>
<source><![CDATA[The Journal of Machine Learning Research]]></source>
<year>2011</year>
<volume>12</volume>
<page-range>2493-537</page-range><publisher-name><![CDATA[JMLR]]></publisher-name>
</nlm-citation>
</ref>
<ref id="B7">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Hinton]]></surname>
<given-names><![CDATA[G. E.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning distributed representations of concepts]]></source>
<year>1986</year>
<conf-name><![CDATA[ eighth annual conference of the cognitive science society]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B8">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mikolov]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Corrado]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Dean]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Efficient estimation of word representations in vector space]]></source>
<year>2013</year>
<conf-name><![CDATA[ Workshop at ICLR]]></conf-name>
<conf-date>2013</conf-date>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B9">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mikolov]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Sutskever]]></surname>
<given-names><![CDATA[I.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[K.]]></given-names>
</name>
<name>
<surname><![CDATA[Corrado]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
<name>
<surname><![CDATA[Dean]]></surname>
<given-names><![CDATA[J.]]></given-names>
</name>
</person-group>
<source><![CDATA[Distributed representations of words and phrases and their compositionality]]></source>
<year>2013</year>
<conf-name><![CDATA[ NIPS]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B10">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Mikolov]]></surname>
<given-names><![CDATA[T.]]></given-names>
</name>
<name>
<surname><![CDATA[Yih]]></surname>
<given-names><![CDATA[W.-t.]]></given-names>
</name>
<name>
<surname><![CDATA[Zweig]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
</person-group>
<source><![CDATA[Linguistic regularities in continuous space Word representations]]></source>
<year>2013</year>
<conf-name><![CDATA[ NAACL HLT]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B11">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Miller]]></surname>
<given-names><![CDATA[G.]]></given-names>
</name>
</person-group>
<source><![CDATA[Wordnet: A lexical database for english]]></source>
<year>1995</year>
<conf-name><![CDATA[ Communications of the ACM]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B12">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Socher]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
<name>
<surname><![CDATA[Chen]]></surname>
<given-names><![CDATA[D.]]></given-names>
</name>
<name>
<surname><![CDATA[Manning]]></surname>
<given-names><![CDATA[C. D.]]></given-names>
</name>
<name>
<surname><![CDATA[Ng]]></surname>
<given-names><![CDATA[A. Y.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning new facts from knowledge bases with neural tensor networks and semantic word vectors]]></source>
<year>2013</year>
<conf-name><![CDATA[ Advances in Neural Information Processing Systems]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B13">
<nlm-citation citation-type="confpro">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Srivastava]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Salakhutdinov]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
</person-group>
<source><![CDATA[Learning representations for multimodal data with deep belief nets]]></source>
<year>2012</year>
<conf-name><![CDATA[ ICML Representation Learning Workshop]]></conf-name>
<conf-loc> </conf-loc>
</nlm-citation>
</ref>
<ref id="B14">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Multimodal learning with deep boltzmann machines]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Srivastava]]></surname>
<given-names><![CDATA[N.]]></given-names>
</name>
<name>
<surname><![CDATA[Salakhutdinov]]></surname>
<given-names><![CDATA[R.]]></given-names>
</name>
</person-group>
<source><![CDATA[Journal of Machine Learning Research]]></source>
<year>2014</year>
</nlm-citation>
</ref>
<ref id="B15">
<nlm-citation citation-type="">
<person-group person-group-type="author">
<name>
<surname><![CDATA[Xu]]></surname>
<given-names><![CDATA[W.]]></given-names>
</name>
<name>
<surname><![CDATA[Rudnicky]]></surname>
<given-names><![CDATA[A. I.]]></given-names>
</name>
</person-group>
<source><![CDATA[Can artificial neural networks learn language models?]]></source>
<year>2000</year>
</nlm-citation>
</ref>
<ref id="B16">
<nlm-citation citation-type="journal">
<article-title xml:lang=""><![CDATA[Knowledge base completion by learning pairwise-interaction differentiated embeddings]]></article-title>
<person-group person-group-type="author">
<name>
<surname><![CDATA[Zhao Y]]></surname>
<given-names><![CDATA[G. P.]]></given-names>
</name>
<name>
<surname><![CDATA[Gao]]></surname>
<given-names><![CDATA[S.]]></given-names>
</name>
</person-group>
<source><![CDATA[Data Mining and Knowledge Discovery]]></source>
<year>2015</year>
<volume>29</volume>
<page-range>1486-504</page-range></nlm-citation>
</ref>
</ref-list>
</back>
</article>
