@inproceedings{sproat-etal-2014-database,
title = "A Database for Measuring Linguistic Information Content",
author = "Sproat, Richard and
Cartoni, Bruno and
Choe, HyunJeong and
Huynh, David and
Ha, Linne and
Rajakumar, Ravindran and
Wenzel-Grondie, Evelyn",
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/47_Paper.pdf",
pages = "967--974",
abstract = "Which languages convey the most information in a given amount of space? This is a question often asked of linguists, especially by engineers who often have some information theoretic measure of information in mind, but rarely define exactly how they would measure that information. The question is, in fact remarkably hard to answer, and many linguists consider it unanswerable. But it is a question that seems as if it ought to have an answer. If one had a database of close translations between a set of typologically diverse languages, with detailed marking of morphosyntactic and morphosemantic features, one could hope to quantify the differences between how these different languages convey information. Since no appropriate database exists we decided to construct one. The purpose of this paper is to present our work on the database, along with some preliminary results. We plan to release the dataset once complete.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sproat-etal-2014-database">
<titleInfo>
<title>A Database for Measuring Linguistic Information Content</title>
</titleInfo>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Sproat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bruno</namePart>
<namePart type="family">Cartoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">HyunJeong</namePart>
<namePart type="family">Choe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Huynh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linne</namePart>
<namePart type="family">Ha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravindran</namePart>
<namePart type="family">Rajakumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evelyn</namePart>
<namePart type="family">Wenzel-Grondie</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>Which languages convey the most information in a given amount of space? This is a question often asked of linguists, especially by engineers who often have some information theoretic measure of information in mind, but rarely define exactly how they would measure that information. The question is, in fact remarkably hard to answer, and many linguists consider it unanswerable. But it is a question that seems as if it ought to have an answer. If one had a database of close translations between a set of typologically diverse languages, with detailed marking of morphosyntactic and morphosemantic features, one could hope to quantify the differences between how these different languages convey information. Since no appropriate database exists we decided to construct one. The purpose of this paper is to present our work on the database, along with some preliminary results. We plan to release the dataset once complete.</abstract>
<identifier type="citekey">sproat-etal-2014-database</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/47_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>967</start>
<end>974</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Database for Measuring Linguistic Information Content
%A Sproat, Richard
%A Cartoni, Bruno
%A Choe, HyunJeong
%A Huynh, David
%A Ha, Linne
%A Rajakumar, Ravindran
%A Wenzel-Grondie, Evelyn
%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 sproat-etal-2014-database
%X Which languages convey the most information in a given amount of space? This is a question often asked of linguists, especially by engineers who often have some information theoretic measure of information in mind, but rarely define exactly how they would measure that information. The question is, in fact remarkably hard to answer, and many linguists consider it unanswerable. But it is a question that seems as if it ought to have an answer. If one had a database of close translations between a set of typologically diverse languages, with detailed marking of morphosyntactic and morphosemantic features, one could hope to quantify the differences between how these different languages convey information. Since no appropriate database exists we decided to construct one. The purpose of this paper is to present our work on the database, along with some preliminary results. We plan to release the dataset once complete.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/47_Paper.pdf
%P 967-974
Markdown (Informal)
[A Database for Measuring Linguistic Information Content](http://www.lrec-conf.org/proceedings/lrec2014/pdf/47_Paper.pdf) (Sproat et al., LREC 2014)
ACL
- Richard Sproat, Bruno Cartoni, HyunJeong Choe, David Huynh, Linne Ha, Ravindran Rajakumar, and Evelyn Wenzel-Grondie. 2014. A Database for Measuring Linguistic Information Content. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 967–974, Reykjavik, Iceland. European Language Resources Association (ELRA).