<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sedghi-sabharwal-2018-knowledge">
    <titleInfo>
        <title>Knowledge Completion for Generics using Guided Tensor Factorization</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Hanie</namePart>
        <namePart type="family">Sedghi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ashish</namePart>
        <namePart type="family">Sabharwal</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2018</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>Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as “all trees produce oxygen” or “some animals live in forests”, we consider the problem of inferring additional such facts at a precision similar to that of the starting KB. Such KBs capture general knowledge about the world, and are crucial for various applications such as question answering. Different from commonly studied named entity KBs such as Freebase, generics KBs involve quantification, have more complex underlying regularities, tend to be more incomplete, and violate the commonly used locally closed world assumption (LCWA). We show that existing KB completion methods struggle with this new task, and present the first approach that is successful. Our results demonstrate that external information, such as relation schemas and entity taxonomies, if used appropriately, can be a surprisingly powerful tool in this setting. First, our simple yet effective knowledge guided tensor factorization approach achieves state-of-the-art results on two generics KBs (80% precise) for science, doubling their size at 74%–86% precision. Second, our novel taxonomy guided, submodular, active learning method for collecting annotations about rare entities (e.g., oriole, a bird) is 6x more effective at inferring further new facts about them than multiple active learning baselines.</abstract>
    <identifier type="citekey">sedghi-sabharwal-2018-knowledge</identifier>
    <identifier type="doi">10.1162/tacl_a_00015</identifier>
    <location>
        <url>https://aclanthology.org/Q18-1015</url>
    </location>
    <part>
        <date>2018</date>
        <detail type="volume"><number>6</number></detail>
        <extent unit="page">
            <start>197</start>
            <end>210</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Journal Article
%T Knowledge Completion for Generics using Guided Tensor Factorization
%A Sedghi, Hanie
%A Sabharwal, Ashish
%J Transactions of the Association for Computational Linguistics
%D 2018
%V 6
%I MIT Press
%C Cambridge, MA
%F sedghi-sabharwal-2018-knowledge
%X Given a knowledge base or KB containing (noisy) facts about common nouns or generics, such as “all trees produce oxygen” or “some animals live in forests”, we consider the problem of inferring additional such facts at a precision similar to that of the starting KB. Such KBs capture general knowledge about the world, and are crucial for various applications such as question answering. Different from commonly studied named entity KBs such as Freebase, generics KBs involve quantification, have more complex underlying regularities, tend to be more incomplete, and violate the commonly used locally closed world assumption (LCWA). We show that existing KB completion methods struggle with this new task, and present the first approach that is successful. Our results demonstrate that external information, such as relation schemas and entity taxonomies, if used appropriately, can be a surprisingly powerful tool in this setting. First, our simple yet effective knowledge guided tensor factorization approach achieves state-of-the-art results on two generics KBs (80% precise) for science, doubling their size at 74%–86% precision. Second, our novel taxonomy guided, submodular, active learning method for collecting annotations about rare entities (e.g., oriole, a bird) is 6x more effective at inferring further new facts about them than multiple active learning baselines.
%R 10.1162/tacl_a_00015
%U https://aclanthology.org/Q18-1015
%U https://doi.org/10.1162/tacl_a_00015
%P 197-210

Markdown (Informal)

[Knowledge Completion for Generics using Guided Tensor Factorization](https://aclanthology.org/Q18-1015) (Sedghi & Sabharwal, TACL 2018)

• Knowledge Completion for Generics using Guided Tensor Factorization (Sedghi & Sabharwal, TACL 2018)

ACL

• Hanie Sedghi and Ashish Sabharwal. 2018. Knowledge Completion for Generics using Guided Tensor Factorization. Transactions of the Association for Computational Linguistics, 6:197–210.