@inproceedings{ambati-etal-2012-word,
title = "Word Sketches for {T}urkish",
author = "Ambati, Bharat Ram and
Reddy, Siva and
Kilgarriff, Adam",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/585_Paper.pdf",
pages = "2945--2950",
abstract = "Word sketches are one-page, automatic, corpus-based summaries of a word's grammatical and collocational behaviour. In this paper we present word sketches for Turkish. Until now, word sketches have been generated using a purpose-built finite-state grammars. Here, we use an existing dependency parser. We describe the process of collecting a 42 million word corpus, parsing it, and generating word sketches from it. We evaluate the word sketches in comparison with word sketches from a language independent sketch grammar on an external evaluation task called topic coherence, using Turkish WordNet to derive an evaluation set of coherent topics.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ambati-etal-2012-word">
<titleInfo>
<title>Word Sketches for Turkish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharat</namePart>
<namePart type="given">Ram</namePart>
<namePart type="family">Ambati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siva</namePart>
<namePart type="family">Reddy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adam</namePart>
<namePart type="family">Kilgarriff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Word sketches are one-page, automatic, corpus-based summaries of a word’s grammatical and collocational behaviour. In this paper we present word sketches for Turkish. Until now, word sketches have been generated using a purpose-built finite-state grammars. Here, we use an existing dependency parser. We describe the process of collecting a 42 million word corpus, parsing it, and generating word sketches from it. We evaluate the word sketches in comparison with word sketches from a language independent sketch grammar on an external evaluation task called topic coherence, using Turkish WordNet to derive an evaluation set of coherent topics.</abstract>
<identifier type="citekey">ambati-etal-2012-word</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/585_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>2945</start>
<end>2950</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Word Sketches for Turkish
%A Ambati, Bharat Ram
%A Reddy, Siva
%A Kilgarriff, Adam
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F ambati-etal-2012-word
%X Word sketches are one-page, automatic, corpus-based summaries of a word’s grammatical and collocational behaviour. In this paper we present word sketches for Turkish. Until now, word sketches have been generated using a purpose-built finite-state grammars. Here, we use an existing dependency parser. We describe the process of collecting a 42 million word corpus, parsing it, and generating word sketches from it. We evaluate the word sketches in comparison with word sketches from a language independent sketch grammar on an external evaluation task called topic coherence, using Turkish WordNet to derive an evaluation set of coherent topics.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/585_Paper.pdf
%P 2945-2950
Markdown (Informal)
[Word Sketches for Turkish](http://www.lrec-conf.org/proceedings/lrec2012/pdf/585_Paper.pdf) (Ambati et al., LREC 2012)
ACL
- Bharat Ram Ambati, Siva Reddy, and Adam Kilgarriff. 2012. Word Sketches for Turkish. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 2945–2950, Istanbul, Turkey. European Language Resources Association (ELRA).