@inproceedings{khokhlova-zakharov-2010-studying,
title = "Studying Word Sketches for {R}ussian",
author = "Khokhlova, Maria and
Zakharov, Victor",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/21_Paper.pdf",
abstract = "Without any doubt corpora are vital tools for linguistic studies and solution for applied tasks. Although corpora opportunities are very useful, there is a need of another kind of software for further improvement of linguistic research as it is impossible to process huge amount of linguistic data manually. The Sketch Engine representing itself a corpus tool which takes as input a corpus of any language and corresponding grammar patterns. The paper describes the writing of Sketch grammar for the Russian language as a part of the Sketch Engine system. The system gives information about a words collocability on concrete dependency models, and generates lists of the most frequent phrases for a given word based on appropriate models. The paper deals with two different approaches to writing rules for the grammar, based on morphological information, and also with applying word sketches to the Russian language. The data evidences that such results may find an extensive use in various fields of linguistics, such as dictionary compiling, language learning and teaching, translation (including machine translation), phraseology, information retrieval etc.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="khokhlova-zakharov-2010-studying">
<titleInfo>
<title>Studying Word Sketches for Russian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Khokhlova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victor</namePart>
<namePart type="family">Zakharov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Without any doubt corpora are vital tools for linguistic studies and solution for applied tasks. Although corpora opportunities are very useful, there is a need of another kind of software for further improvement of linguistic research as it is impossible to process huge amount of linguistic data manually. The Sketch Engine representing itself a corpus tool which takes as input a corpus of any language and corresponding grammar patterns. The paper describes the writing of Sketch grammar for the Russian language as a part of the Sketch Engine system. The system gives information about a words collocability on concrete dependency models, and generates lists of the most frequent phrases for a given word based on appropriate models. The paper deals with two different approaches to writing rules for the grammar, based on morphological information, and also with applying word sketches to the Russian language. The data evidences that such results may find an extensive use in various fields of linguistics, such as dictionary compiling, language learning and teaching, translation (including machine translation), phraseology, information retrieval etc.</abstract>
<identifier type="citekey">khokhlova-zakharov-2010-studying</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/21_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Studying Word Sketches for Russian
%A Khokhlova, Maria
%A Zakharov, Victor
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F khokhlova-zakharov-2010-studying
%X Without any doubt corpora are vital tools for linguistic studies and solution for applied tasks. Although corpora opportunities are very useful, there is a need of another kind of software for further improvement of linguistic research as it is impossible to process huge amount of linguistic data manually. The Sketch Engine representing itself a corpus tool which takes as input a corpus of any language and corresponding grammar patterns. The paper describes the writing of Sketch grammar for the Russian language as a part of the Sketch Engine system. The system gives information about a words collocability on concrete dependency models, and generates lists of the most frequent phrases for a given word based on appropriate models. The paper deals with two different approaches to writing rules for the grammar, based on morphological information, and also with applying word sketches to the Russian language. The data evidences that such results may find an extensive use in various fields of linguistics, such as dictionary compiling, language learning and teaching, translation (including machine translation), phraseology, information retrieval etc.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/21_Paper.pdf
Markdown (Informal)
[Studying Word Sketches for Russian](http://www.lrec-conf.org/proceedings/lrec2010/pdf/21_Paper.pdf) (Khokhlova & Zakharov, LREC 2010)
ACL
- Maria Khokhlova and Victor Zakharov. 2010. Studying Word Sketches for Russian. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10), Valletta, Malta. European Language Resources Association (ELRA).