@inproceedings{bitew-etal-2021-lazy,
title = "Lazy Low-Resource Coreference Resolution: a Study on Leveraging Black-Box Translation Tools",
author = "Bitew, Semere Kiros and
Deleu, Johannes and
Develder, Chris and
Demeester, Thomas",
editor = "Ogrodniczuk, Maciej and
Pradhan, Sameer and
Poesio, Massimo and
Grishina, Yulia and
Ng, Vincent",
booktitle = "Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.crac-1.6/",
doi = "10.18653/v1/2021.crac-1.6",
pages = "57--62",
abstract = "Large annotated corpora for coreference resolution are available for few languages. For machine translation, however, strong black-box systems exist for many languages. We empirically explore the appealing idea of leveraging such translation tools for bootstrapping coreference resolution in languages with limited resources. Two scenarios are analyzed, in which a large coreference corpus in a high-resource language is used for coreference predictions in a smaller language, i.e., by machine translating either the training corpus or the test data. In our empirical evaluation of coreference resolution using the two scenarios on several medium-resource languages, we find no improvement over monolingual baseline models. Our analysis of the various sources of error inherent to the studied scenarios, reveals that in fact the quality of contemporary machine translation tools is the main limiting factor."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bitew-etal-2021-lazy">
<titleInfo>
<title>Lazy Low-Resource Coreference Resolution: a Study on Leveraging Black-Box Translation Tools</title>
</titleInfo>
<name type="personal">
<namePart type="given">Semere</namePart>
<namePart type="given">Kiros</namePart>
<namePart type="family">Bitew</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johannes</namePart>
<namePart type="family">Deleu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chris</namePart>
<namePart type="family">Develder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Demeester</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maciej</namePart>
<namePart type="family">Ogrodniczuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sameer</namePart>
<namePart type="family">Pradhan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Massimo</namePart>
<namePart type="family">Poesio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulia</namePart>
<namePart type="family">Grishina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large annotated corpora for coreference resolution are available for few languages. For machine translation, however, strong black-box systems exist for many languages. We empirically explore the appealing idea of leveraging such translation tools for bootstrapping coreference resolution in languages with limited resources. Two scenarios are analyzed, in which a large coreference corpus in a high-resource language is used for coreference predictions in a smaller language, i.e., by machine translating either the training corpus or the test data. In our empirical evaluation of coreference resolution using the two scenarios on several medium-resource languages, we find no improvement over monolingual baseline models. Our analysis of the various sources of error inherent to the studied scenarios, reveals that in fact the quality of contemporary machine translation tools is the main limiting factor.</abstract>
<identifier type="citekey">bitew-etal-2021-lazy</identifier>
<identifier type="doi">10.18653/v1/2021.crac-1.6</identifier>
<location>
<url>https://aclanthology.org/2021.crac-1.6/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>57</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lazy Low-Resource Coreference Resolution: a Study on Leveraging Black-Box Translation Tools
%A Bitew, Semere Kiros
%A Deleu, Johannes
%A Develder, Chris
%A Demeester, Thomas
%Y Ogrodniczuk, Maciej
%Y Pradhan, Sameer
%Y Poesio, Massimo
%Y Grishina, Yulia
%Y Ng, Vincent
%S Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F bitew-etal-2021-lazy
%X Large annotated corpora for coreference resolution are available for few languages. For machine translation, however, strong black-box systems exist for many languages. We empirically explore the appealing idea of leveraging such translation tools for bootstrapping coreference resolution in languages with limited resources. Two scenarios are analyzed, in which a large coreference corpus in a high-resource language is used for coreference predictions in a smaller language, i.e., by machine translating either the training corpus or the test data. In our empirical evaluation of coreference resolution using the two scenarios on several medium-resource languages, we find no improvement over monolingual baseline models. Our analysis of the various sources of error inherent to the studied scenarios, reveals that in fact the quality of contemporary machine translation tools is the main limiting factor.
%R 10.18653/v1/2021.crac-1.6
%U https://aclanthology.org/2021.crac-1.6/
%U https://doi.org/10.18653/v1/2021.crac-1.6
%P 57-62
Markdown (Informal)
[Lazy Low-Resource Coreference Resolution: a Study on Leveraging Black-Box Translation Tools](https://aclanthology.org/2021.crac-1.6/) (Bitew et al., CRAC 2021)
ACL