<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marcheggiani-titov-2016-discrete">
    <titleInfo>
        <title>Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Diego</namePart>
        <namePart type="family">Marcheggiani</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ivan</namePart>
        <namePart type="family">Titov</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2016</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <genre authority="bibutilsgt">journal article</genre>
    <relatedItem type="host">
        <titleInfo>
            <title>Transactions of the Association for Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <issuance>continuing</issuance>
            <publisher>MIT Press</publisher>
            <place>
                <placeTerm type="text">Cambridge, MA</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">periodical</genre>
        <genre authority="bibutilsgt">academic journal</genre>
    </relatedItem>
    <abstract>We present a method for unsupervised open-domain relation discovery. In contrast to previous (mostly generative and agglomerative clustering) approaches, our model relies on rich contextual features and makes minimal independence assumptions. The model is composed of two parts: a feature-rich relation extractor, which predicts a semantic relation between two entities, and a factorization model, which reconstructs arguments (i.e., the entities) relying on the predicted relation. The two components are estimated jointly so as to minimize errors in recovering arguments. We study factorization models inspired by previous work in relation factorization and selectional preference modeling. Our models substantially outperform the generative and agglomerative-clustering counterparts and achieve state-of-the-art performance.</abstract>
    <identifier type="citekey">marcheggiani-titov-2016-discrete</identifier>
    <identifier type="doi">10.1162/tacl_a_00095</identifier>
    <location>
        <url>https://aclanthology.org/Q16-1017</url>
    </location>
    <part>
        <date>2016</date>
        <detail type="volume"><number>4</number></detail>
        <extent unit="page">
            <start>231</start>
            <end>244</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations
%A Marcheggiani, Diego
%A Titov, Ivan
%J Transactions of the Association for Computational Linguistics
%D 2016
%V 4
%I MIT Press
%C Cambridge, MA
%F marcheggiani-titov-2016-discrete
%X We present a method for unsupervised open-domain relation discovery. In contrast to previous (mostly generative and agglomerative clustering) approaches, our model relies on rich contextual features and makes minimal independence assumptions. The model is composed of two parts: a feature-rich relation extractor, which predicts a semantic relation between two entities, and a factorization model, which reconstructs arguments (i.e., the entities) relying on the predicted relation. The two components are estimated jointly so as to minimize errors in recovering arguments. We study factorization models inspired by previous work in relation factorization and selectional preference modeling. Our models substantially outperform the generative and agglomerative-clustering counterparts and achieve state-of-the-art performance.
%R 10.1162/tacl_a_00095
%U https://aclanthology.org/Q16-1017
%U https://doi.org/10.1162/tacl_a_00095
%P 231-244

Markdown (Informal)

[Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations](https://aclanthology.org/Q16-1017) (Marcheggiani & Titov, TACL 2016)

• Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations (Marcheggiani & Titov, TACL 2016)

ACL

• Diego Marcheggiani and Ivan Titov. 2016. Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations. Transactions of the Association for Computational Linguistics, 4:231–244.