@inproceedings{wong-2010-semantic,
title = "Semantic Evaluation of Machine Translation",
author = "Wong, Billy Tak-Ming",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/837_Paper.pdf",
abstract = "It is recognized that many evaluation metrics of machine translation in use that focus on surface word level suffer from their lack of tolerance of linguistic variance, and the incorporation of linguistic features can improve their performance. To this end, WordNet is therefore widely utilized by recent evaluation metrics as a thesaurus for identifying synonym pairs. On this basis, word pairs in similar meaning, however, are still neglected. We investigate the significance of this particular word group to the performance of evaluation metrics. In our experiments we integrate eight different measures of lexical semantic similarity into an evaluation metric based on standard measures of unigram precision, recall and F-measure. It is found that a knowledge-based measure proposed by Wu and Palmer and a corpus-based measure, namely Latent Semantic Analysis, lead to an observable gain in correlation with human judgments of translation quality, in an extent to which better than the use of WordNet for synonyms.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wong-2010-semantic">
<titleInfo>
<title>Semantic Evaluation of Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Billy</namePart>
<namePart type="given">Tak-Ming</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">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>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>It is recognized that many evaluation metrics of machine translation in use that focus on surface word level suffer from their lack of tolerance of linguistic variance, and the incorporation of linguistic features can improve their performance. To this end, WordNet is therefore widely utilized by recent evaluation metrics as a thesaurus for identifying synonym pairs. On this basis, word pairs in similar meaning, however, are still neglected. We investigate the significance of this particular word group to the performance of evaluation metrics. In our experiments we integrate eight different measures of lexical semantic similarity into an evaluation metric based on standard measures of unigram precision, recall and F-measure. It is found that a knowledge-based measure proposed by Wu and Palmer and a corpus-based measure, namely Latent Semantic Analysis, lead to an observable gain in correlation with human judgments of translation quality, in an extent to which better than the use of WordNet for synonyms.</abstract>
<identifier type="citekey">wong-2010-semantic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/837_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Semantic Evaluation of Machine Translation
%A Wong, Billy Tak-Ming
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F wong-2010-semantic
%X It is recognized that many evaluation metrics of machine translation in use that focus on surface word level suffer from their lack of tolerance of linguistic variance, and the incorporation of linguistic features can improve their performance. To this end, WordNet is therefore widely utilized by recent evaluation metrics as a thesaurus for identifying synonym pairs. On this basis, word pairs in similar meaning, however, are still neglected. We investigate the significance of this particular word group to the performance of evaluation metrics. In our experiments we integrate eight different measures of lexical semantic similarity into an evaluation metric based on standard measures of unigram precision, recall and F-measure. It is found that a knowledge-based measure proposed by Wu and Palmer and a corpus-based measure, namely Latent Semantic Analysis, lead to an observable gain in correlation with human judgments of translation quality, in an extent to which better than the use of WordNet for synonyms.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/837_Paper.pdf
Markdown (Informal)
[Semantic Evaluation of Machine Translation](http://www.lrec-conf.org/proceedings/lrec2010/pdf/837_Paper.pdf) (Wong, LREC 2010)
ACL
- Billy Tak-Ming Wong. 2010. Semantic Evaluation of Machine Translation. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).