@inproceedings{stymne-ahrenberg-2012-practice,
title = "On the practice of error analysis for machine translation evaluation",
author = "Stymne, Sara and
Ahrenberg, Lars",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}`12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L12-1417/",
pages = "1785--1790",
abstract = "Error analysis is a means to assess machine translation output in qualitative terms, which can be used as a basis for the generation of error profiles for different systems. As for other subjective approaches to evaluation it runs the risk of low inter-annotator agreement, but very often in papers applying error analysis to MT, this aspect is not even discussed. In this paper, we report results from a comparative evaluation of two systems where agreement initially was low, and discuss the different ways we used to improve it. We compared the effects of using more or less fine-grained taxonomies, and the possibility to restrict analysis to short sentences only. We report results on inter-annotator agreement before and after measures were taken, on error categories that are most likely to be confused, and on the possibility to establish error profiles also in the absence of a high inter-annotator agreement."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stymne-ahrenberg-2012-practice">
<titleInfo>
<title>On the practice of error analysis for machine translation evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lars</namePart>
<namePart type="family">Ahrenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC‘12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Error analysis is a means to assess machine translation output in qualitative terms, which can be used as a basis for the generation of error profiles for different systems. As for other subjective approaches to evaluation it runs the risk of low inter-annotator agreement, but very often in papers applying error analysis to MT, this aspect is not even discussed. In this paper, we report results from a comparative evaluation of two systems where agreement initially was low, and discuss the different ways we used to improve it. We compared the effects of using more or less fine-grained taxonomies, and the possibility to restrict analysis to short sentences only. We report results on inter-annotator agreement before and after measures were taken, on error categories that are most likely to be confused, and on the possibility to establish error profiles also in the absence of a high inter-annotator agreement.</abstract>
<identifier type="citekey">stymne-ahrenberg-2012-practice</identifier>
<location>
<url>https://aclanthology.org/L12-1417/</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>1785</start>
<end>1790</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T On the practice of error analysis for machine translation evaluation
%A Stymne, Sara
%A Ahrenberg, Lars
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC‘12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F stymne-ahrenberg-2012-practice
%X Error analysis is a means to assess machine translation output in qualitative terms, which can be used as a basis for the generation of error profiles for different systems. As for other subjective approaches to evaluation it runs the risk of low inter-annotator agreement, but very often in papers applying error analysis to MT, this aspect is not even discussed. In this paper, we report results from a comparative evaluation of two systems where agreement initially was low, and discuss the different ways we used to improve it. We compared the effects of using more or less fine-grained taxonomies, and the possibility to restrict analysis to short sentences only. We report results on inter-annotator agreement before and after measures were taken, on error categories that are most likely to be confused, and on the possibility to establish error profiles also in the absence of a high inter-annotator agreement.
%U https://aclanthology.org/L12-1417/
%P 1785-1790
Markdown (Informal)
[On the practice of error analysis for machine translation evaluation](https://aclanthology.org/L12-1417/) (Stymne & Ahrenberg, LREC 2012)
ACL