@inproceedings{vuckovic-etal-2008-rule,
title = "Rule-Based Chunker for {C}roatian",
author = "Vu{\v{c}}kovi{\'c}, Kristina and
Tadi{\'c}, Marko and
Dovedan, Zdravko",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/631_paper.pdf",
abstract = "In this paper we discuss a rule-based approach to chunking sentences in Croatian, implemented using local regular grammars within the NooJ development environment. We describe the rules and their implementation by regular grammars and at the same time show that in NooJ environment it is extremely easy to fine tune their different sub-rules. Since Croatian has strong morphosyntactic features that are shared between most or all elements of a chunk, the rules are built by taking these features into account and strongly relying on them. For the evaluation of our chunker we used a extracted set of manually annotated sentences from 100 kw MSD/tagged and disambiguated Croatian corpus. Our chunker performed the best on VP-chunks (F: 97.01), while NP-chunks (F: 92.31) and PP-chunks (F: 83.08) were of lower quality. The results are comparable to chunker performance of CoNLL-2000 shared task of chunking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vuckovic-etal-2008-rule">
<titleInfo>
<title>Rule-Based Chunker for Croatian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Vučković</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Tadić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zdravko</namePart>
<namePart type="family">Dovedan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we discuss a rule-based approach to chunking sentences in Croatian, implemented using local regular grammars within the NooJ development environment. We describe the rules and their implementation by regular grammars and at the same time show that in NooJ environment it is extremely easy to fine tune their different sub-rules. Since Croatian has strong morphosyntactic features that are shared between most or all elements of a chunk, the rules are built by taking these features into account and strongly relying on them. For the evaluation of our chunker we used a extracted set of manually annotated sentences from 100 kw MSD/tagged and disambiguated Croatian corpus. Our chunker performed the best on VP-chunks (F: 97.01), while NP-chunks (F: 92.31) and PP-chunks (F: 83.08) were of lower quality. The results are comparable to chunker performance of CoNLL-2000 shared task of chunking.</abstract>
<identifier type="citekey">vuckovic-etal-2008-rule</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/631_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rule-Based Chunker for Croatian
%A Vučković, Kristina
%A Tadić, Marko
%A Dovedan, Zdravko
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F vuckovic-etal-2008-rule
%X In this paper we discuss a rule-based approach to chunking sentences in Croatian, implemented using local regular grammars within the NooJ development environment. We describe the rules and their implementation by regular grammars and at the same time show that in NooJ environment it is extremely easy to fine tune their different sub-rules. Since Croatian has strong morphosyntactic features that are shared between most or all elements of a chunk, the rules are built by taking these features into account and strongly relying on them. For the evaluation of our chunker we used a extracted set of manually annotated sentences from 100 kw MSD/tagged and disambiguated Croatian corpus. Our chunker performed the best on VP-chunks (F: 97.01), while NP-chunks (F: 92.31) and PP-chunks (F: 83.08) were of lower quality. The results are comparable to chunker performance of CoNLL-2000 shared task of chunking.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/631_paper.pdf
Markdown (Informal)
[Rule-Based Chunker for Croatian](http://www.lrec-conf.org/proceedings/lrec2008/pdf/631_paper.pdf) (Vučković et al., LREC 2008)
ACL
- Kristina Vučković, Marko Tadić, and Zdravko Dovedan. 2008. Rule-Based Chunker for Croatian. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).