@inproceedings{shimazu-etal-2020-evaluation,
title = "Evaluation Dataset for Zero Pronoun in {J}apanese to {E}nglish Translation",
author = "Shimazu, Sho and
Takase, Sho and
Nakazawa, Toshiaki and
Okazaki, Naoaki",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.447",
pages = "3630--3634",
abstract = "In natural language, we often omit some words that are easily understandable from the context. In particular, pronouns of subject, object, and possessive cases are often omitted in Japanese; these are known as zero pronouns. In translation from Japanese to other languages, we need to find a correct antecedent for each zero pronoun to generate a correct and coherent translation. However, it is difficult for conventional automatic evaluation metrics (e.g., BLEU) to focus on the success of zero pronoun resolution. Therefore, we present a hand-crafted dataset to evaluate whether translation models can resolve the zero pronoun problems in Japanese to English translations. We manually and statistically validate that our dataset can effectively evaluate the correctness of the antecedents selected in translations. Through the translation experiments using our dataset, we reveal shortcomings of an existing context-aware neural machine translation model.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shimazu-etal-2020-evaluation">
<titleInfo>
<title>Evaluation Dataset for Zero Pronoun in Japanese to English Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Shimazu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sho</namePart>
<namePart type="family">Takase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Toshiaki</namePart>
<namePart type="family">Nakazawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In natural language, we often omit some words that are easily understandable from the context. In particular, pronouns of subject, object, and possessive cases are often omitted in Japanese; these are known as zero pronouns. In translation from Japanese to other languages, we need to find a correct antecedent for each zero pronoun to generate a correct and coherent translation. However, it is difficult for conventional automatic evaluation metrics (e.g., BLEU) to focus on the success of zero pronoun resolution. Therefore, we present a hand-crafted dataset to evaluate whether translation models can resolve the zero pronoun problems in Japanese to English translations. We manually and statistically validate that our dataset can effectively evaluate the correctness of the antecedents selected in translations. Through the translation experiments using our dataset, we reveal shortcomings of an existing context-aware neural machine translation model.</abstract>
<identifier type="citekey">shimazu-etal-2020-evaluation</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.447</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>3630</start>
<end>3634</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluation Dataset for Zero Pronoun in Japanese to English Translation
%A Shimazu, Sho
%A Takase, Sho
%A Nakazawa, Toshiaki
%A Okazaki, Naoaki
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F shimazu-etal-2020-evaluation
%X In natural language, we often omit some words that are easily understandable from the context. In particular, pronouns of subject, object, and possessive cases are often omitted in Japanese; these are known as zero pronouns. In translation from Japanese to other languages, we need to find a correct antecedent for each zero pronoun to generate a correct and coherent translation. However, it is difficult for conventional automatic evaluation metrics (e.g., BLEU) to focus on the success of zero pronoun resolution. Therefore, we present a hand-crafted dataset to evaluate whether translation models can resolve the zero pronoun problems in Japanese to English translations. We manually and statistically validate that our dataset can effectively evaluate the correctness of the antecedents selected in translations. Through the translation experiments using our dataset, we reveal shortcomings of an existing context-aware neural machine translation model.
%U https://aclanthology.org/2020.lrec-1.447
%P 3630-3634
Markdown (Informal)
[Evaluation Dataset for Zero Pronoun in Japanese to English Translation](https://aclanthology.org/2020.lrec-1.447) (Shimazu et al., LREC 2020)
ACL