@inproceedings{sharma-etal-2022-mtlens,
title = "{MTL}ens: Machine Translation Output Debugging",
author = "Sharma, Shreyas and
Darwish, Kareem and
Pavanelli, Lucas and
Castro Ferreira, Thiago and
Al-Badrashiny, Mohamed and
Yuksel, Kamer Ali and
Sawaf, Hassan",
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-1.448/",
pages = "4221--4226",
abstract = "The performance of Machine Translation (MT) systems varies significantly with inputs of diverging features such as topics, genres, and surface properties. Though there are many MT evaluation metrics that generally correlate with human judgments, they are not directly useful in identifying specific shortcomings of MT systems. In this demo, we present a benchmarking interface that enables improved evaluation of specific MT systems in isolation or multiple MT systems collectively by quantitatively evaluating their performance on many tasks across multiple domains and evaluation metrics. Further, it facilitates effective debugging and error analysis of MT output via the use of dynamic filters that help users hone in on problem sentences with specific properties, such as genre, topic, sentence length, etc. The interface can be extended to include additional filters such as lexical, morphological, and syntactic features. Aside from helping debug MT output, it can also help in identifying problems in reference translations and evaluation metrics."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sharma-etal-2022-mtlens">
<titleInfo>
<title>MTLens: Machine Translation Output Debugging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shreyas</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Pavanelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thiago</namePart>
<namePart type="family">Castro Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohamed</namePart>
<namePart type="family">Al-Badrashiny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kamer</namePart>
<namePart type="given">Ali</namePart>
<namePart type="family">Yuksel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hassan</namePart>
<namePart type="family">Sawaf</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>The performance of Machine Translation (MT) systems varies significantly with inputs of diverging features such as topics, genres, and surface properties. Though there are many MT evaluation metrics that generally correlate with human judgments, they are not directly useful in identifying specific shortcomings of MT systems. In this demo, we present a benchmarking interface that enables improved evaluation of specific MT systems in isolation or multiple MT systems collectively by quantitatively evaluating their performance on many tasks across multiple domains and evaluation metrics. Further, it facilitates effective debugging and error analysis of MT output via the use of dynamic filters that help users hone in on problem sentences with specific properties, such as genre, topic, sentence length, etc. The interface can be extended to include additional filters such as lexical, morphological, and syntactic features. Aside from helping debug MT output, it can also help in identifying problems in reference translations and evaluation metrics.</abstract>
<identifier type="citekey">sharma-etal-2022-mtlens</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.448/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4221</start>
<end>4226</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MTLens: Machine Translation Output Debugging
%A Sharma, Shreyas
%A Darwish, Kareem
%A Pavanelli, Lucas
%A Castro Ferreira, Thiago
%A Al-Badrashiny, Mohamed
%A Yuksel, Kamer Ali
%A Sawaf, Hassan
%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 sharma-etal-2022-mtlens
%X The performance of Machine Translation (MT) systems varies significantly with inputs of diverging features such as topics, genres, and surface properties. Though there are many MT evaluation metrics that generally correlate with human judgments, they are not directly useful in identifying specific shortcomings of MT systems. In this demo, we present a benchmarking interface that enables improved evaluation of specific MT systems in isolation or multiple MT systems collectively by quantitatively evaluating their performance on many tasks across multiple domains and evaluation metrics. Further, it facilitates effective debugging and error analysis of MT output via the use of dynamic filters that help users hone in on problem sentences with specific properties, such as genre, topic, sentence length, etc. The interface can be extended to include additional filters such as lexical, morphological, and syntactic features. Aside from helping debug MT output, it can also help in identifying problems in reference translations and evaluation metrics.
%U https://aclanthology.org/2022.lrec-1.448/
%P 4221-4226
Markdown (Informal)
[MTLens: Machine Translation Output Debugging](https://aclanthology.org/2022.lrec-1.448/) (Sharma et al., LREC 2022)
ACL
- Shreyas Sharma, Kareem Darwish, Lucas Pavanelli, Thiago Castro Ferreira, Mohamed Al-Badrashiny, Kamer Ali Yuksel, and Hassan Sawaf. 2022. MTLens: Machine Translation Output Debugging. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 4221–4226, Marseille, France. European Language Resources Association.