@inproceedings{vuckovic-etal-2010-improving,
title = "Improving Chunking Accuracy on {C}roatian Texts by Morphosyntactic Tagging",
author = "Vu{\v{c}}kovi{\'c}, Kristina and
Agi{\'c}, {\v{Z}}eljko and
Tadi{\'c}, Marko",
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/834_Paper.pdf",
abstract = "In this paper, we present the results of an experiment with utilizing a stochastic morphosyntactic tagger as a pre-processing module of a rule-based chunker and partial parser for Croatian in order to raise its overall chunking and partial parsing accuracy on Croatian texts. In order to conduct the experiment, we have manually chunked and partially parsed 459 sentences from the Croatia Weekly 100 kw newspaper sub-corpus taken from the Croatian National Corpus, that were previously also morphosyntactically disambiguated and lemmatized. Due to the lack of resources of this type, these sentences were designated as a temporary chunking and partial parsing gold standard for Croatian. We have then evaluated the chunker and partial parser in three different scenarios: (1) chunking previously morphosyntactically untagged text, (2) chunking text that was tagged using the stochastic morphosyntactic tagger for Croatian and (3) chunking manually tagged text. The obtained F1-scores for the three scenarios were, respectively, 0.874 (P: 0.825, R: 0.930), 0.891 (P: 0.856, R: 0.928) and 0.914 (P: 0.904, R: 0.925). The paper provides the description of language resources and tools used in the experiment, its setup and discussion of results and perspectives for future work.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vuckovic-etal-2010-improving">
<titleInfo>
<title>Improving Chunking Accuracy on Croatian Texts by Morphosyntactic Tagging</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">Željko</namePart>
<namePart type="family">Agić</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>
<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>In this paper, we present the results of an experiment with utilizing a stochastic morphosyntactic tagger as a pre-processing module of a rule-based chunker and partial parser for Croatian in order to raise its overall chunking and partial parsing accuracy on Croatian texts. In order to conduct the experiment, we have manually chunked and partially parsed 459 sentences from the Croatia Weekly 100 kw newspaper sub-corpus taken from the Croatian National Corpus, that were previously also morphosyntactically disambiguated and lemmatized. Due to the lack of resources of this type, these sentences were designated as a temporary chunking and partial parsing gold standard for Croatian. We have then evaluated the chunker and partial parser in three different scenarios: (1) chunking previously morphosyntactically untagged text, (2) chunking text that was tagged using the stochastic morphosyntactic tagger for Croatian and (3) chunking manually tagged text. The obtained F1-scores for the three scenarios were, respectively, 0.874 (P: 0.825, R: 0.930), 0.891 (P: 0.856, R: 0.928) and 0.914 (P: 0.904, R: 0.925). The paper provides the description of language resources and tools used in the experiment, its setup and discussion of results and perspectives for future work.</abstract>
<identifier type="citekey">vuckovic-etal-2010-improving</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/834_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Chunking Accuracy on Croatian Texts by Morphosyntactic Tagging
%A Vučković, Kristina
%A Agić, Željko
%A Tadić, Marko
%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 vuckovic-etal-2010-improving
%X In this paper, we present the results of an experiment with utilizing a stochastic morphosyntactic tagger as a pre-processing module of a rule-based chunker and partial parser for Croatian in order to raise its overall chunking and partial parsing accuracy on Croatian texts. In order to conduct the experiment, we have manually chunked and partially parsed 459 sentences from the Croatia Weekly 100 kw newspaper sub-corpus taken from the Croatian National Corpus, that were previously also morphosyntactically disambiguated and lemmatized. Due to the lack of resources of this type, these sentences were designated as a temporary chunking and partial parsing gold standard for Croatian. We have then evaluated the chunker and partial parser in three different scenarios: (1) chunking previously morphosyntactically untagged text, (2) chunking text that was tagged using the stochastic morphosyntactic tagger for Croatian and (3) chunking manually tagged text. The obtained F1-scores for the three scenarios were, respectively, 0.874 (P: 0.825, R: 0.930), 0.891 (P: 0.856, R: 0.928) and 0.914 (P: 0.904, R: 0.925). The paper provides the description of language resources and tools used in the experiment, its setup and discussion of results and perspectives for future work.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/834_Paper.pdf
Markdown (Informal)
[Improving Chunking Accuracy on Croatian Texts by Morphosyntactic Tagging](http://www.lrec-conf.org/proceedings/lrec2010/pdf/834_Paper.pdf) (Vučković et al., LREC 2010)
ACL