@inproceedings{hashemi-hwa-2014-comparison,
title = "A Comparison of {MT} Errors and {ESL} Errors",
author = "Hashemi, Homa B. and
Hwa, Rebecca",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/911_Paper.pdf",
pages = "2696--2700",
abstract = "Generating fluent and grammatical sentences is a major goal for both Machine Translation (MT) and second-language Grammar Error Correction (GEC), but there have not been a lot of cross-fertilization between the two research communities. Arguably, an automatic translate-to-English system might be seen as an English as a Second Language (ESL) writer whose native language is the source language. This paper investigates whether research findings from the GEC community may help with characterizing MT error analysis. We describe a method for the automatic classification of MT errors according to English as a Second Language (ESL) error categories and conduct a large comparison experiment that includes both high-performing and low-performing translate-to-English MT systems for several source languages. Comparing the distribution of MT error types for all the systems suggests that MT systems have fairly similar distributions regardless of their source languages, and the high-performing MT systems have error distributions that are more similar to those of the low-performing MT systems than to those of ESL learners with the same L1.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hashemi-hwa-2014-comparison">
<titleInfo>
<title>A Comparison of MT Errors and ESL Errors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Homa</namePart>
<namePart type="given">B</namePart>
<namePart type="family">Hashemi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Hwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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 (ELRA)</publisher>
<place>
<placeTerm type="text">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Generating fluent and grammatical sentences is a major goal for both Machine Translation (MT) and second-language Grammar Error Correction (GEC), but there have not been a lot of cross-fertilization between the two research communities. Arguably, an automatic translate-to-English system might be seen as an English as a Second Language (ESL) writer whose native language is the source language. This paper investigates whether research findings from the GEC community may help with characterizing MT error analysis. We describe a method for the automatic classification of MT errors according to English as a Second Language (ESL) error categories and conduct a large comparison experiment that includes both high-performing and low-performing translate-to-English MT systems for several source languages. Comparing the distribution of MT error types for all the systems suggests that MT systems have fairly similar distributions regardless of their source languages, and the high-performing MT systems have error distributions that are more similar to those of the low-performing MT systems than to those of ESL learners with the same L1.</abstract>
<identifier type="citekey">hashemi-hwa-2014-comparison</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/911_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>2696</start>
<end>2700</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Comparison of MT Errors and ESL Errors
%A Hashemi, Homa B.
%A Hwa, Rebecca
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F hashemi-hwa-2014-comparison
%X Generating fluent and grammatical sentences is a major goal for both Machine Translation (MT) and second-language Grammar Error Correction (GEC), but there have not been a lot of cross-fertilization between the two research communities. Arguably, an automatic translate-to-English system might be seen as an English as a Second Language (ESL) writer whose native language is the source language. This paper investigates whether research findings from the GEC community may help with characterizing MT error analysis. We describe a method for the automatic classification of MT errors according to English as a Second Language (ESL) error categories and conduct a large comparison experiment that includes both high-performing and low-performing translate-to-English MT systems for several source languages. Comparing the distribution of MT error types for all the systems suggests that MT systems have fairly similar distributions regardless of their source languages, and the high-performing MT systems have error distributions that are more similar to those of the low-performing MT systems than to those of ESL learners with the same L1.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/911_Paper.pdf
%P 2696-2700
Markdown (Informal)
[A Comparison of MT Errors and ESL Errors](http://www.lrec-conf.org/proceedings/lrec2014/pdf/911_Paper.pdf) (Hashemi & Hwa, LREC 2014)
ACL
- Homa B. Hashemi and Rebecca Hwa. 2014. A Comparison of MT Errors and ESL Errors. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 2696–2700, Reykjavik, Iceland. European Language Resources Association (ELRA).