@inproceedings{hurtado-2022-bilinmid,
title = "{BIL}in{MID}: A {S}panish-{E}nglish Corpus of the {US} Midwest",
author = "Hurtado, Irati",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.590",
pages = "5511--5516",
abstract = "This paper describes the Bilinguals in the Midwest (BILinMID) Corpus, a comparable text corpus of the Spanish and English spoken in the US Midwest by various types of bilinguals. Unlike other areas within the US where language contact has been widely documented (e.g., the Southwest), Spanish-English bilingualism in the Midwest has been understudied despite an increase in its Hispanic population. The BILinMID Corpus contains short stories narrated in Spanish and in English by 72 speakers representing different types of bilinguals: early simultaneous bilinguals, early sequential bilinguals, and late second language learners. All stories have been transcribed and annotated using various natural language processing tools. Additionally, a user interface has also been created to facilitate searching for specific patterns in the corpus as well as to filter out results according to specified criteria. Guidelines and procedures followed to create the corpus and the user interface are described in detail in the paper. The corpus is fully available online and it might be particularly interesting for researchers working on language variation and contact.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hurtado-2022-bilinmid">
<titleInfo>
<title>BILinMID: A Spanish-English Corpus of the US Midwest</title>
</titleInfo>
<name type="personal">
<namePart type="given">Irati</namePart>
<namePart type="family">Hurtado</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>This paper describes the Bilinguals in the Midwest (BILinMID) Corpus, a comparable text corpus of the Spanish and English spoken in the US Midwest by various types of bilinguals. Unlike other areas within the US where language contact has been widely documented (e.g., the Southwest), Spanish-English bilingualism in the Midwest has been understudied despite an increase in its Hispanic population. The BILinMID Corpus contains short stories narrated in Spanish and in English by 72 speakers representing different types of bilinguals: early simultaneous bilinguals, early sequential bilinguals, and late second language learners. All stories have been transcribed and annotated using various natural language processing tools. Additionally, a user interface has also been created to facilitate searching for specific patterns in the corpus as well as to filter out results according to specified criteria. Guidelines and procedures followed to create the corpus and the user interface are described in detail in the paper. The corpus is fully available online and it might be particularly interesting for researchers working on language variation and contact.</abstract>
<identifier type="citekey">hurtado-2022-bilinmid</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.590</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5511</start>
<end>5516</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BILinMID: A Spanish-English Corpus of the US Midwest
%A Hurtado, Irati
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F hurtado-2022-bilinmid
%X This paper describes the Bilinguals in the Midwest (BILinMID) Corpus, a comparable text corpus of the Spanish and English spoken in the US Midwest by various types of bilinguals. Unlike other areas within the US where language contact has been widely documented (e.g., the Southwest), Spanish-English bilingualism in the Midwest has been understudied despite an increase in its Hispanic population. The BILinMID Corpus contains short stories narrated in Spanish and in English by 72 speakers representing different types of bilinguals: early simultaneous bilinguals, early sequential bilinguals, and late second language learners. All stories have been transcribed and annotated using various natural language processing tools. Additionally, a user interface has also been created to facilitate searching for specific patterns in the corpus as well as to filter out results according to specified criteria. Guidelines and procedures followed to create the corpus and the user interface are described in detail in the paper. The corpus is fully available online and it might be particularly interesting for researchers working on language variation and contact.
%U https://aclanthology.org/2022.lrec-1.590
%P 5511-5516
Markdown (Informal)
[BILinMID: A Spanish-English Corpus of the US Midwest](https://aclanthology.org/2022.lrec-1.590) (Hurtado, LREC 2022)
ACL