@inproceedings{kazakov-etal-2017-machine,
title = "Machine Learning Models of Universal Grammar Parameter Dependencies",
author = "Kazakov, Dimitar and
Cordoni, Guido and
Ceolin, Andrea and
Irimia, Monica-Alexandrina and
Kim, Shin-Sook and
Michelioudakis, Dimitris and
Radkevich, Nina and
Guardiano, Cristina and
Longobardi, Giuseppe",
editor = "Zervanou, Kalliopi and
Osenova, Petya and
Wandl-Vogt, Eveline and
Cristea, Dan",
booktitle = "Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with {RANLP} 2017",
month = sep,
year = "2017",
address = "Varna",
publisher = "INCOMA Inc.",
url = "https://doi.org/10.26615/978-954-452-040-3_005",
doi = "10.26615/978-954-452-040-3_005",
pages = "31--37",
abstract = "The use of parameters in the description of natural language syntax has to balance between the need to discriminate among (sometimes subtly different) languages, which can be seen as a cross-linguistic version of Chomsky{'}s (1964) descriptive adequacy, and the complexity of the acquisition task that a large number of parameters would imply, which is a problem for explanatory adequacy. Here we present a novel approach in which a machine learning algorithm is used to find dependencies in a table of parameters. The result is a dependency graph in which some of the parameters can be fully predicted from others. These empirical findings can be then subjected to linguistic analysis, which may either refute them by providing typological counter-examples of languages not included in the original dataset, dismiss them on theoretical grounds, or uphold them as tentative empirical laws worth of further study.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kazakov-etal-2017-machine">
<titleInfo>
<title>Machine Learning Models of Universal Grammar Parameter Dependencies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitar</namePart>
<namePart type="family">Kazakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Cordoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Ceolin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monica-Alexandrina</namePart>
<namePart type="family">Irimia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shin-Sook</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dimitris</namePart>
<namePart type="family">Michelioudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nina</namePart>
<namePart type="family">Radkevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Guardiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Longobardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kalliopi</namePart>
<namePart type="family">Zervanou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petya</namePart>
<namePart type="family">Osenova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eveline</namePart>
<namePart type="family">Wandl-Vogt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Cristea</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Inc.</publisher>
<place>
<placeTerm type="text">Varna</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The use of parameters in the description of natural language syntax has to balance between the need to discriminate among (sometimes subtly different) languages, which can be seen as a cross-linguistic version of Chomsky’s (1964) descriptive adequacy, and the complexity of the acquisition task that a large number of parameters would imply, which is a problem for explanatory adequacy. Here we present a novel approach in which a machine learning algorithm is used to find dependencies in a table of parameters. The result is a dependency graph in which some of the parameters can be fully predicted from others. These empirical findings can be then subjected to linguistic analysis, which may either refute them by providing typological counter-examples of languages not included in the original dataset, dismiss them on theoretical grounds, or uphold them as tentative empirical laws worth of further study.</abstract>
<identifier type="citekey">kazakov-etal-2017-machine</identifier>
<identifier type="doi">10.26615/978-954-452-040-3_005</identifier>
<part>
<date>2017-09</date>
<extent unit="page">
<start>31</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Machine Learning Models of Universal Grammar Parameter Dependencies
%A Kazakov, Dimitar
%A Cordoni, Guido
%A Ceolin, Andrea
%A Irimia, Monica-Alexandrina
%A Kim, Shin-Sook
%A Michelioudakis, Dimitris
%A Radkevich, Nina
%A Guardiano, Cristina
%A Longobardi, Giuseppe
%Y Zervanou, Kalliopi
%Y Osenova, Petya
%Y Wandl-Vogt, Eveline
%Y Cristea, Dan
%S Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017
%D 2017
%8 September
%I INCOMA Inc.
%C Varna
%F kazakov-etal-2017-machine
%X The use of parameters in the description of natural language syntax has to balance between the need to discriminate among (sometimes subtly different) languages, which can be seen as a cross-linguistic version of Chomsky’s (1964) descriptive adequacy, and the complexity of the acquisition task that a large number of parameters would imply, which is a problem for explanatory adequacy. Here we present a novel approach in which a machine learning algorithm is used to find dependencies in a table of parameters. The result is a dependency graph in which some of the parameters can be fully predicted from others. These empirical findings can be then subjected to linguistic analysis, which may either refute them by providing typological counter-examples of languages not included in the original dataset, dismiss them on theoretical grounds, or uphold them as tentative empirical laws worth of further study.
%R 10.26615/978-954-452-040-3_005
%U https://doi.org/10.26615/978-954-452-040-3_005
%P 31-37
Markdown (Informal)
[Machine Learning Models of Universal Grammar Parameter Dependencies](https://doi.org/10.26615/978-954-452-040-3_005) (Kazakov et al., RANLP 2017)
ACL
- Dimitar Kazakov, Guido Cordoni, Andrea Ceolin, Monica-Alexandrina Irimia, Shin-Sook Kim, Dimitris Michelioudakis, Nina Radkevich, Cristina Guardiano, and Giuseppe Longobardi. 2017. Machine Learning Models of Universal Grammar Parameter Dependencies. In Proceedings of the Workshop Knowledge Resources for the Socio-Economic Sciences and Humanities associated with RANLP 2017, pages 31–37, Varna. INCOMA Inc..