@inproceedings{maxwelll-smith-etal-2020-applications,
title = "Applications of Natural Language Processing in Bilingual Language Teaching: An {I}ndonesian-{E}nglish Case Study",
author = "Maxwell-Smith, Zara and
Gonz{\'a}lez Ochoa, Sim{\'o}n and
Foley, Ben and
Suominen, Hanna",
editor = "Burstein, Jill and
Kochmar, Ekaterina and
Leacock, Claudia and
Madnani, Nitin and
Pil{\'a}n, Ildik{\'o} and
Yannakoudakis, Helen and
Zesch, Torsten",
booktitle = "Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications",
month = jul,
year = "2020",
address = "Seattle, WA, USA → Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.bea-1.12",
doi = "10.18653/v1/2020.bea-1.12",
pages = "124--134",
abstract = "Multilingual corpora are difficult to compile and a classroom setting adds pedagogy to the mix of factors which make this data so rich and problematic to classify. In this paper, we set out methodological considerations of using automated speech recognition to build a corpus of teacher speech in an Indonesian language classroom. Our preliminary results (64{\%} word error rate) suggest these tools have the potential to speed data collection in this context. We provide practical examples of our data structure, details of our piloted computer-assisted processes, and fine-grained error analysis. Our study is informed and directed by genuine research questions and discussion in both the education and computational linguistics fields. We highlight some of the benefits and risks of using these emerging technologies to analyze the complex work of language teachers and in education more generally.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="maxwelll-smith-etal-2020-applications">
<titleInfo>
<title>Applications of Natural Language Processing in Bilingual Language Teaching: An Indonesian-English Case Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zara</namePart>
<namePart type="family">Maxwell-Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simón</namePart>
<namePart type="family">González Ochoa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Foley</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hanna</namePart>
<namePart type="family">Suominen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitin</namePart>
<namePart type="family">Madnani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ildikó</namePart>
<namePart type="family">Pilán</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Torsten</namePart>
<namePart type="family">Zesch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, WA, USA → Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Multilingual corpora are difficult to compile and a classroom setting adds pedagogy to the mix of factors which make this data so rich and problematic to classify. In this paper, we set out methodological considerations of using automated speech recognition to build a corpus of teacher speech in an Indonesian language classroom. Our preliminary results (64% word error rate) suggest these tools have the potential to speed data collection in this context. We provide practical examples of our data structure, details of our piloted computer-assisted processes, and fine-grained error analysis. Our study is informed and directed by genuine research questions and discussion in both the education and computational linguistics fields. We highlight some of the benefits and risks of using these emerging technologies to analyze the complex work of language teachers and in education more generally.</abstract>
<identifier type="citekey">maxwelll-smith-etal-2020-applications</identifier>
<identifier type="doi">10.18653/v1/2020.bea-1.12</identifier>
<location>
<url>https://aclanthology.org/2020.bea-1.12</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>124</start>
<end>134</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Applications of Natural Language Processing in Bilingual Language Teaching: An Indonesian-English Case Study
%A Maxwell-Smith, Zara
%A González Ochoa, Simón
%A Foley, Ben
%A Suominen, Hanna
%Y Burstein, Jill
%Y Kochmar, Ekaterina
%Y Leacock, Claudia
%Y Madnani, Nitin
%Y Pilán, Ildikó
%Y Yannakoudakis, Helen
%Y Zesch, Torsten
%S Proceedings of the Fifteenth Workshop on Innovative Use of NLP for Building Educational Applications
%D 2020
%8 July
%I Association for Computational Linguistics
%C Seattle, WA, USA → Online
%F maxwelll-smith-etal-2020-applications
%X Multilingual corpora are difficult to compile and a classroom setting adds pedagogy to the mix of factors which make this data so rich and problematic to classify. In this paper, we set out methodological considerations of using automated speech recognition to build a corpus of teacher speech in an Indonesian language classroom. Our preliminary results (64% word error rate) suggest these tools have the potential to speed data collection in this context. We provide practical examples of our data structure, details of our piloted computer-assisted processes, and fine-grained error analysis. Our study is informed and directed by genuine research questions and discussion in both the education and computational linguistics fields. We highlight some of the benefits and risks of using these emerging technologies to analyze the complex work of language teachers and in education more generally.
%R 10.18653/v1/2020.bea-1.12
%U https://aclanthology.org/2020.bea-1.12
%U https://doi.org/10.18653/v1/2020.bea-1.12
%P 124-134
Markdown (Informal)
[Applications of Natural Language Processing in Bilingual Language Teaching: An Indonesian-English Case Study](https://aclanthology.org/2020.bea-1.12) (Maxwell-Smith et al., BEA 2020)
ACL