<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="simova-uszkoreit-2017-word">
    <titleInfo>
        <title>Word Embeddings as Features for Supervised Coreference Resolution</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Iliana</namePart>
        <namePart type="family">Simova</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hans</namePart>
        <namePart type="family">Uszkoreit</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2017-09</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ruslan</namePart>
            <namePart type="family">Mitkov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Galia</namePart>
            <namePart type="family">Angelova</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>INCOMA Ltd.</publisher>
            <place>
                <placeTerm type="text">Varna, Bulgaria</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>A common reason for errors in coreference resolution is the lack of semantic information to help determine the compatibility between mentions referring to the same entity. Distributed representations, which have been shown successful in encoding relatedness between words, could potentially be a good source of such knowledge. Moreover, being obtained in an unsupervised manner, they could help address data sparsity issues in labeled training data at a small cost. In this work we investigate whether and to what extend features derived from word embeddings can be successfully used for supervised coreference resolution. We experiment with several word embedding models, and several different types of embeddingbased features, including embedding cluster and cosine similarity-based features. Our evaluations show improvements in the performance of a supervised state-of-theart coreference system.</abstract>
    <identifier type="citekey">simova-uszkoreit-2017-word</identifier>
    <identifier type="doi">10.26615/978-954-452-049-6_088</identifier>
    <part>
        <date>2017-09</date>
        <extent unit="page">
            <start>686</start>
            <end>693</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Word Embeddings as Features for Supervised Coreference Resolution
%A Simova, Iliana
%A Uszkoreit, Hans
%Y Mitkov, Ruslan
%Y Angelova, Galia
%S Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017
%D 2017
%8 September
%I INCOMA Ltd.
%C Varna, Bulgaria
%F simova-uszkoreit-2017-word
%X A common reason for errors in coreference resolution is the lack of semantic information to help determine the compatibility between mentions referring to the same entity. Distributed representations, which have been shown successful in encoding relatedness between words, could potentially be a good source of such knowledge. Moreover, being obtained in an unsupervised manner, they could help address data sparsity issues in labeled training data at a small cost. In this work we investigate whether and to what extend features derived from word embeddings can be successfully used for supervised coreference resolution. We experiment with several word embedding models, and several different types of embeddingbased features, including embedding cluster and cosine similarity-based features. Our evaluations show improvements in the performance of a supervised state-of-theart coreference system.
%R 10.26615/978-954-452-049-6_088
%U https://doi.org/10.26615/978-954-452-049-6_088
%P 686-693

Markdown (Informal)

[Word Embeddings as Features for Supervised Coreference Resolution](https://doi.org/10.26615/978-954-452-049-6_088) (Simova & Uszkoreit, RANLP 2017)

• Word Embeddings as Features for Supervised Coreference Resolution (Simova & Uszkoreit, RANLP 2017)

ACL

• Iliana Simova and Hans Uszkoreit. 2017. Word Embeddings as Features for Supervised Coreference Resolution. In Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017, pages 686–693, Varna, Bulgaria. INCOMA Ltd..