@inproceedings{davidson-etal-2020-developing-nlp,
title = "Developing {NLP} Tools with a New Corpus of Learner {S}panish",
author = "Davidson, Sam and
Yamada, Aaron and
Fernandez Mira, Paloma and
Carando, Agustina and
Sanchez Gutierrez, Claudia H. and
Sagae, Kenji",
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-1.894",
pages = "7238--7243",
abstract = "The development of effective NLP tools for the L2 classroom depends largely on the availability of large annotated corpora of language learner text. While annotated learner corpora of English are widely available, large learner corpora of Spanish are less common. Those Spanish corpora that are available do not contain the annotations needed to facilitate the development of tools beneficial to language learners, such as grammatical error correction. As a result, the field has seen little research in NLP tools designed to benefit Spanish language learners and teachers. We introduce COWS-L2H, a freely available corpus of Spanish learner data which includes error annotations and parallel corrected text to help researchers better understand L2 development, to examine teaching practices empirically, and to develop NLP tools to better serve the Spanish teaching community. We demonstrate the utility of this corpus by developing a neural-network based grammatical error correction system for Spanish learner writing.",
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="davidson-etal-2020-developing-nlp">
<titleInfo>
<title>Developing NLP Tools with a New Corpus of Learner Spanish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sam</namePart>
<namePart type="family">Davidson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Yamada</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paloma</namePart>
<namePart type="family">Fernandez Mira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agustina</namePart>
<namePart type="family">Carando</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Sanchez Gutierrez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kenji</namePart>
<namePart type="family">Sagae</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>The development of effective NLP tools for the L2 classroom depends largely on the availability of large annotated corpora of language learner text. While annotated learner corpora of English are widely available, large learner corpora of Spanish are less common. Those Spanish corpora that are available do not contain the annotations needed to facilitate the development of tools beneficial to language learners, such as grammatical error correction. As a result, the field has seen little research in NLP tools designed to benefit Spanish language learners and teachers. We introduce COWS-L2H, a freely available corpus of Spanish learner data which includes error annotations and parallel corrected text to help researchers better understand L2 development, to examine teaching practices empirically, and to develop NLP tools to better serve the Spanish teaching community. We demonstrate the utility of this corpus by developing a neural-network based grammatical error correction system for Spanish learner writing.</abstract>
<identifier type="citekey">davidson-etal-2020-developing-nlp</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.894</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>7238</start>
<end>7243</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing NLP Tools with a New Corpus of Learner Spanish
%A Davidson, Sam
%A Yamada, Aaron
%A Fernandez Mira, Paloma
%A Carando, Agustina
%A Sanchez Gutierrez, Claudia H.
%A Sagae, Kenji
%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 davidson-etal-2020-developing-nlp
%X The development of effective NLP tools for the L2 classroom depends largely on the availability of large annotated corpora of language learner text. While annotated learner corpora of English are widely available, large learner corpora of Spanish are less common. Those Spanish corpora that are available do not contain the annotations needed to facilitate the development of tools beneficial to language learners, such as grammatical error correction. As a result, the field has seen little research in NLP tools designed to benefit Spanish language learners and teachers. We introduce COWS-L2H, a freely available corpus of Spanish learner data which includes error annotations and parallel corrected text to help researchers better understand L2 development, to examine teaching practices empirically, and to develop NLP tools to better serve the Spanish teaching community. We demonstrate the utility of this corpus by developing a neural-network based grammatical error correction system for Spanish learner writing.
%U https://aclanthology.org/2020.lrec-1.894
%P 7238-7243
Markdown (Informal)
[Developing NLP Tools with a New Corpus of Learner Spanish](https://aclanthology.org/2020.lrec-1.894) (Davidson et al., LREC 2020)
ACL
- Sam Davidson, Aaron Yamada, Paloma Fernandez Mira, Agustina Carando, Claudia H. Sanchez Gutierrez, and Kenji Sagae. 2020. Developing NLP Tools with a New Corpus of Learner Spanish. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 7238–7243, Marseille, France. European Language Resources Association.