@inproceedings{grimes-etal-2012-automatic,
title = "Automatic word alignment tools to scale production of manually aligned parallel texts",
author = "Grimes, Stephen and
Peterson, Katherine and
Li, Xuansong",
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 = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/487_Paper.pdf",
pages = "2194--2198",
abstract = "We have been creating large-scale manual word alignment corpora for Arabic-English and Chinese-English language pairs in genres such as newsire, broadcast news and conversation, and web blogs. We are now meeting the challenge of word aligning further varieties of web data for Chinese and Arabic ''''''``dialects''''''''. Human word alignment annotation can be costly and arduous. Alignment guidelines may be imprecise or underspecified in cases where parallel sentences are hard to compare -- due to non-literal translations or differences between language structures. In order to speed annotation, we examine the effect that seeding manual alignments with automatic aligner output has on annotation speed and accuracy. We use automatic alignment methods that produce alignment results which are high precision and low recall to minimize annotator corrections. Results suggest that annotation time can be reduced by up to 20{\%}, but we also found that reviewing and correcting automatic alignments requires more time than anticipated. We discuss throughout the paper crucial decisions on data structures for word alignment that likely have a significant impact on our results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grimes-etal-2012-automatic">
<titleInfo>
<title>Automatic word alignment tools to scale production of manually aligned parallel texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Grimes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katherine</namePart>
<namePart type="family">Peterson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuansong</namePart>
<namePart type="family">Li</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>We have been creating large-scale manual word alignment corpora for Arabic-English and Chinese-English language pairs in genres such as newsire, broadcast news and conversation, and web blogs. We are now meeting the challenge of word aligning further varieties of web data for Chinese and Arabic ”””“dialects””””. Human word alignment annotation can be costly and arduous. Alignment guidelines may be imprecise or underspecified in cases where parallel sentences are hard to compare – due to non-literal translations or differences between language structures. In order to speed annotation, we examine the effect that seeding manual alignments with automatic aligner output has on annotation speed and accuracy. We use automatic alignment methods that produce alignment results which are high precision and low recall to minimize annotator corrections. Results suggest that annotation time can be reduced by up to 20%, but we also found that reviewing and correcting automatic alignments requires more time than anticipated. We discuss throughout the paper crucial decisions on data structures for word alignment that likely have a significant impact on our results.</abstract>
<identifier type="citekey">grimes-etal-2012-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/487_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2194</start>
<end>2198</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic word alignment tools to scale production of manually aligned parallel texts
%A Grimes, Stephen
%A Peterson, Katherine
%A Li, Xuansong
%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 grimes-etal-2012-automatic
%X We have been creating large-scale manual word alignment corpora for Arabic-English and Chinese-English language pairs in genres such as newsire, broadcast news and conversation, and web blogs. We are now meeting the challenge of word aligning further varieties of web data for Chinese and Arabic ”””“dialects””””. Human word alignment annotation can be costly and arduous. Alignment guidelines may be imprecise or underspecified in cases where parallel sentences are hard to compare – due to non-literal translations or differences between language structures. In order to speed annotation, we examine the effect that seeding manual alignments with automatic aligner output has on annotation speed and accuracy. We use automatic alignment methods that produce alignment results which are high precision and low recall to minimize annotator corrections. Results suggest that annotation time can be reduced by up to 20%, but we also found that reviewing and correcting automatic alignments requires more time than anticipated. We discuss throughout the paper crucial decisions on data structures for word alignment that likely have a significant impact on our results.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/487_Paper.pdf
%P 2194-2198
Markdown (Informal)
[Automatic word alignment tools to scale production of manually aligned parallel texts](http://www.lrec-conf.org/proceedings/lrec2012/pdf/487_Paper.pdf) (Grimes et al., LREC 2012)
ACL