@inproceedings{bentivogli-etal-2016-wags,
title = "{WAGS}: A Beautiful {E}nglish-{I}talian Benchmark Supporting Word Alignment Evaluation on Rare Words",
author = "Bentivogli, Luisa and
Cettolo, Mauro and
Farajian, M. Amin and
Federico, Marcello",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1562",
pages = "3535--3542",
abstract = "This paper presents WAGS (Word Alignment Gold Standard), a novel benchmark which allows extensive evaluation of WA tools on out-of-vocabulary (OOV) and rare words. WAGS is a subset of the Common Test section of the Europarl English-Italian parallel corpus, and is specifically tailored to OOV and rare words. WAGS is composed of 6,715 sentence pairs containing 11,958 occurrences of OOV and rare words up to frequency 15 in the Europarl Training set (5,080 English words and 6,878 Italian words), representing almost 3{\%} of the whole text. Since WAGS is focused on OOV/rare words, manual alignments are provided for these words only, and not for the whole sentences. Two off-the-shelf word aligners have been evaluated on WAGS, and results have been compared to those obtained on an existing benchmark tailored to full text alignment. The results obtained confirm that WAGS is a valuable resource, which allows a statistically sound evaluation of WA systems{'} performance on OOV and rare words, as well as extensive data analyses. WAGS is publicly released under a Creative Commons Attribution license.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bentivogli-etal-2016-wags">
<titleInfo>
<title>WAGS: A Beautiful English-Italian Benchmark Supporting Word Alignment Evaluation on Rare Words</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luisa</namePart>
<namePart type="family">Bentivogli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mauro</namePart>
<namePart type="family">Cettolo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">M</namePart>
<namePart type="given">Amin</namePart>
<namePart type="family">Farajian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents WAGS (Word Alignment Gold Standard), a novel benchmark which allows extensive evaluation of WA tools on out-of-vocabulary (OOV) and rare words. WAGS is a subset of the Common Test section of the Europarl English-Italian parallel corpus, and is specifically tailored to OOV and rare words. WAGS is composed of 6,715 sentence pairs containing 11,958 occurrences of OOV and rare words up to frequency 15 in the Europarl Training set (5,080 English words and 6,878 Italian words), representing almost 3% of the whole text. Since WAGS is focused on OOV/rare words, manual alignments are provided for these words only, and not for the whole sentences. Two off-the-shelf word aligners have been evaluated on WAGS, and results have been compared to those obtained on an existing benchmark tailored to full text alignment. The results obtained confirm that WAGS is a valuable resource, which allows a statistically sound evaluation of WA systems’ performance on OOV and rare words, as well as extensive data analyses. WAGS is publicly released under a Creative Commons Attribution license.</abstract>
<identifier type="citekey">bentivogli-etal-2016-wags</identifier>
<location>
<url>https://aclanthology.org/L16-1562</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3535</start>
<end>3542</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WAGS: A Beautiful English-Italian Benchmark Supporting Word Alignment Evaluation on Rare Words
%A Bentivogli, Luisa
%A Cettolo, Mauro
%A Farajian, M. Amin
%A Federico, Marcello
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F bentivogli-etal-2016-wags
%X This paper presents WAGS (Word Alignment Gold Standard), a novel benchmark which allows extensive evaluation of WA tools on out-of-vocabulary (OOV) and rare words. WAGS is a subset of the Common Test section of the Europarl English-Italian parallel corpus, and is specifically tailored to OOV and rare words. WAGS is composed of 6,715 sentence pairs containing 11,958 occurrences of OOV and rare words up to frequency 15 in the Europarl Training set (5,080 English words and 6,878 Italian words), representing almost 3% of the whole text. Since WAGS is focused on OOV/rare words, manual alignments are provided for these words only, and not for the whole sentences. Two off-the-shelf word aligners have been evaluated on WAGS, and results have been compared to those obtained on an existing benchmark tailored to full text alignment. The results obtained confirm that WAGS is a valuable resource, which allows a statistically sound evaluation of WA systems’ performance on OOV and rare words, as well as extensive data analyses. WAGS is publicly released under a Creative Commons Attribution license.
%U https://aclanthology.org/L16-1562
%P 3535-3542
Markdown (Informal)
[WAGS: A Beautiful English-Italian Benchmark Supporting Word Alignment Evaluation on Rare Words](https://aclanthology.org/L16-1562) (Bentivogli et al., LREC 2016)
ACL