@inproceedings{bjarnadottir-dadason-2014-utilizing,
title = "Utilizing constituent structure for compound analysis",
author = "Bjarnad{\'o}ttir, Krist{\'\i}n and
Da{\dh}ason, J{\'o}n",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/954_Paper.pdf",
abstract = "Compounding is extremely productive in Icelandic and multi-word compounds are common. The likelihood of finding previously unseen compounds in texts is thus very high, which makes out-of-vocabulary words a problem in the use of NLP tools. The tool de-scribed in this paper splits Icelandic compounds and shows their binary constituent structure. The probability of a constituent in an unknown (or unanalysed) compound forming a combined constituent with either of its neighbours is estimated, with the use of data on the constituent structure of over 240 thousand compounds from the Database of Modern Icelandic Inflection, and word frequencies from {\'I}slenskur or{\dh}asj{\'o}{\dh}ur, a corpus of approx. 550 million words. Thus, the structure of an unknown compound is derived by com-parison with compounds with partially the same constituents and similar structure in the training data. The granularity of the split re-turned by the decompounder is important in tasks such as semantic analysis or machine translation, where a flat (non-structured) se-quence of constituents is insufficient.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bjarnadottir-dadason-2014-utilizing">
<titleInfo>
<title>Utilizing constituent structure for compound analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristín</namePart>
<namePart type="family">Bjarnadóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jón</namePart>
<namePart type="family">Da\dhason</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Compounding is extremely productive in Icelandic and multi-word compounds are common. The likelihood of finding previously unseen compounds in texts is thus very high, which makes out-of-vocabulary words a problem in the use of NLP tools. The tool de-scribed in this paper splits Icelandic compounds and shows their binary constituent structure. The probability of a constituent in an unknown (or unanalysed) compound forming a combined constituent with either of its neighbours is estimated, with the use of data on the constituent structure of over 240 thousand compounds from the Database of Modern Icelandic Inflection, and word frequencies from Íslenskur or\dhasjó\dhur, a corpus of approx. 550 million words. Thus, the structure of an unknown compound is derived by com-parison with compounds with partially the same constituents and similar structure in the training data. The granularity of the split re-turned by the decompounder is important in tasks such as semantic analysis or machine translation, where a flat (non-structured) se-quence of constituents is insufficient.</abstract>
<identifier type="citekey">bjarnadottir-dadason-2014-utilizing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/954_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Utilizing constituent structure for compound analysis
%A Bjarnadóttir, Kristín
%A Da\dhason, Jón
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F bjarnadottir-dadason-2014-utilizing
%X Compounding is extremely productive in Icelandic and multi-word compounds are common. The likelihood of finding previously unseen compounds in texts is thus very high, which makes out-of-vocabulary words a problem in the use of NLP tools. The tool de-scribed in this paper splits Icelandic compounds and shows their binary constituent structure. The probability of a constituent in an unknown (or unanalysed) compound forming a combined constituent with either of its neighbours is estimated, with the use of data on the constituent structure of over 240 thousand compounds from the Database of Modern Icelandic Inflection, and word frequencies from Íslenskur or\dhasjó\dhur, a corpus of approx. 550 million words. Thus, the structure of an unknown compound is derived by com-parison with compounds with partially the same constituents and similar structure in the training data. The granularity of the split re-turned by the decompounder is important in tasks such as semantic analysis or machine translation, where a flat (non-structured) se-quence of constituents is insufficient.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/954_Paper.pdf
Markdown (Informal)
[Utilizing constituent structure for compound analysis](http://www.lrec-conf.org/proceedings/lrec2014/pdf/954_Paper.pdf) (Bjarnadóttir & Daðason, LREC 2014)
ACL
- Kristín Bjarnadóttir and Jón Daðason. 2014. Utilizing constituent structure for compound analysis. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), Reykjavik, Iceland. European Language Resources Association (ELRA).