@inproceedings{schrader-2006-non,
title = "Non-probabilistic alignment of rare {G}erman and {E}nglish nominal expressions",
author = "Schrader, Bettina",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/100_pdf.pdf",
abstract = "We present an alignment strategy that specifically deals with the correct alignment of rare German nominal compounds to their English multiword translations. It recognizes compounds and multiwords based on their character lengths and on their most frequent POS-patterns, and aligns them based on their length ratios. Our approach is designed on the basis of a data analysis on roughly 500 German hapax legomena, and as it does not use any frequency or co-occurrence information, it is well-suited to align rare compounds, but also achieves good results for more frequent expressions. Experiment results show that the strategy is able to correctly identify correct translations for 70{\%} of the compound hapaxes in our data set. Additionally, we checked on 700 randomly chosen entries in the dictionary that was automatically generated by our alignment tool. Results of this experiment also indicate that our strategy works for non-hapaxes as well, including finding multiple correct translations for the same head compound.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="schrader-2006-non">
<titleInfo>
<title>Non-probabilistic alignment of rare German and English nominal expressions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bettina</namePart>
<namePart type="family">Schrader</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present an alignment strategy that specifically deals with the correct alignment of rare German nominal compounds to their English multiword translations. It recognizes compounds and multiwords based on their character lengths and on their most frequent POS-patterns, and aligns them based on their length ratios. Our approach is designed on the basis of a data analysis on roughly 500 German hapax legomena, and as it does not use any frequency or co-occurrence information, it is well-suited to align rare compounds, but also achieves good results for more frequent expressions. Experiment results show that the strategy is able to correctly identify correct translations for 70% of the compound hapaxes in our data set. Additionally, we checked on 700 randomly chosen entries in the dictionary that was automatically generated by our alignment tool. Results of this experiment also indicate that our strategy works for non-hapaxes as well, including finding multiple correct translations for the same head compound.</abstract>
<identifier type="citekey">schrader-2006-non</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/100_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Non-probabilistic alignment of rare German and English nominal expressions
%A Schrader, Bettina
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F schrader-2006-non
%X We present an alignment strategy that specifically deals with the correct alignment of rare German nominal compounds to their English multiword translations. It recognizes compounds and multiwords based on their character lengths and on their most frequent POS-patterns, and aligns them based on their length ratios. Our approach is designed on the basis of a data analysis on roughly 500 German hapax legomena, and as it does not use any frequency or co-occurrence information, it is well-suited to align rare compounds, but also achieves good results for more frequent expressions. Experiment results show that the strategy is able to correctly identify correct translations for 70% of the compound hapaxes in our data set. Additionally, we checked on 700 randomly chosen entries in the dictionary that was automatically generated by our alignment tool. Results of this experiment also indicate that our strategy works for non-hapaxes as well, including finding multiple correct translations for the same head compound.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/100_pdf.pdf
Markdown (Informal)
[Non-probabilistic alignment of rare German and English nominal expressions](http://www.lrec-conf.org/proceedings/lrec2006/pdf/100_pdf.pdf) (Schrader, LREC 2006)
ACL