@inproceedings{ramanathan-visweswariah-2012-study,
title = "A Study of Word-Classing for {MT} Reordering",
author = "Ramanathan, Ananthakrishnan and
Visweswariah, Karthik",
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/921_Paper.pdf",
pages = "3971--3976",
abstract = "MT systems typically use parsers to help reorder constituents. However most languages do not have adequate treebank data to learn good parsers, and such training data is extremely time-consuming to annotate. Our earlier work has shown that a reordering model learned from word-alignments using POS tags as features can improve MT performance (Visweswariah et al., 2011). In this paper, we investigate the effect of word-classing on reordering performance using this model. We show that unsupervised word clusters perform somewhat worse but still reasonably well, compared to a part-of-speech (POS) tagger built with a small amount of annotated data; while a richer tag set including case and gender-number-person further improves reordering performance by around 1.2 monolingual BLEU points. While annotating this richer tagset is more complicated than annotating the base tagset, it is much easier than annotating treebank data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ramanathan-visweswariah-2012-study">
<titleInfo>
<title>A Study of Word-Classing for MT Reordering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ananthakrishnan</namePart>
<namePart type="family">Ramanathan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="family">Visweswariah</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>MT systems typically use parsers to help reorder constituents. However most languages do not have adequate treebank data to learn good parsers, and such training data is extremely time-consuming to annotate. Our earlier work has shown that a reordering model learned from word-alignments using POS tags as features can improve MT performance (Visweswariah et al., 2011). In this paper, we investigate the effect of word-classing on reordering performance using this model. We show that unsupervised word clusters perform somewhat worse but still reasonably well, compared to a part-of-speech (POS) tagger built with a small amount of annotated data; while a richer tag set including case and gender-number-person further improves reordering performance by around 1.2 monolingual BLEU points. While annotating this richer tagset is more complicated than annotating the base tagset, it is much easier than annotating treebank data.</abstract>
<identifier type="citekey">ramanathan-visweswariah-2012-study</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/921_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3971</start>
<end>3976</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Study of Word-Classing for MT Reordering
%A Ramanathan, Ananthakrishnan
%A Visweswariah, Karthik
%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 ramanathan-visweswariah-2012-study
%X MT systems typically use parsers to help reorder constituents. However most languages do not have adequate treebank data to learn good parsers, and such training data is extremely time-consuming to annotate. Our earlier work has shown that a reordering model learned from word-alignments using POS tags as features can improve MT performance (Visweswariah et al., 2011). In this paper, we investigate the effect of word-classing on reordering performance using this model. We show that unsupervised word clusters perform somewhat worse but still reasonably well, compared to a part-of-speech (POS) tagger built with a small amount of annotated data; while a richer tag set including case and gender-number-person further improves reordering performance by around 1.2 monolingual BLEU points. While annotating this richer tagset is more complicated than annotating the base tagset, it is much easier than annotating treebank data.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/921_Paper.pdf
%P 3971-3976
Markdown (Informal)
[A Study of Word-Classing for MT Reordering](http://www.lrec-conf.org/proceedings/lrec2012/pdf/921_Paper.pdf) (Ramanathan & Visweswariah, LREC 2012)
ACL
- Ananthakrishnan Ramanathan and Karthik Visweswariah. 2012. A Study of Word-Classing for MT Reordering. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3971–3976, Istanbul, Turkey. European Language Resources Association (ELRA).