@inproceedings{ljubesic-etal-2016-new,
title = "New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of {C}roatian and {S}erbian",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Klubi{\v{c}}ka, Filip and
Agi{\'c}, {\v{Z}}eljko and
Jazbec, Ivo-Pavao",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1676",
pages = "4264--4270",
abstract = "In this paper we present newly developed inflectional lexcions and manually annotated corpora of Croatian and Serbian. We introduce hrLex and srLex - two freely available inflectional lexicons of Croatian and Serbian - and describe the process of building these lexicons, supported by supervised machine learning techniques for lemma and paradigm prediction. Furthermore, we introduce hr500k, a manually annotated corpus of Croatian, 500 thousand tokens in size. We showcase the three newly developed resources on the task of morphosyntactic annotation of both languages by using a recently developed CRF tagger. We achieve best results yet reported on the task for both languages, beating the HunPos baseline trained on the same datasets by a wide margin.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2016-new">
<titleInfo>
<title>New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Klubička</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">Ivo-Pavao</namePart>
<namePart type="family">Jazbec</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</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">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper we present newly developed inflectional lexcions and manually annotated corpora of Croatian and Serbian. We introduce hrLex and srLex - two freely available inflectional lexicons of Croatian and Serbian - and describe the process of building these lexicons, supported by supervised machine learning techniques for lemma and paradigm prediction. Furthermore, we introduce hr500k, a manually annotated corpus of Croatian, 500 thousand tokens in size. We showcase the three newly developed resources on the task of morphosyntactic annotation of both languages by using a recently developed CRF tagger. We achieve best results yet reported on the task for both languages, beating the HunPos baseline trained on the same datasets by a wide margin.</abstract>
<identifier type="citekey">ljubesic-etal-2016-new</identifier>
<location>
<url>https://aclanthology.org/L16-1676</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4264</start>
<end>4270</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian
%A Ljubešić, Nikola
%A Klubička, Filip
%A Agić, Željko
%A Jazbec, Ivo-Pavao
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F ljubesic-etal-2016-new
%X In this paper we present newly developed inflectional lexcions and manually annotated corpora of Croatian and Serbian. We introduce hrLex and srLex - two freely available inflectional lexicons of Croatian and Serbian - and describe the process of building these lexicons, supported by supervised machine learning techniques for lemma and paradigm prediction. Furthermore, we introduce hr500k, a manually annotated corpus of Croatian, 500 thousand tokens in size. We showcase the three newly developed resources on the task of morphosyntactic annotation of both languages by using a recently developed CRF tagger. We achieve best results yet reported on the task for both languages, beating the HunPos baseline trained on the same datasets by a wide margin.
%U https://aclanthology.org/L16-1676
%P 4264-4270
Markdown (Informal)
[New Inflectional Lexicons and Training Corpora for Improved Morphosyntactic Annotation of Croatian and Serbian](https://aclanthology.org/L16-1676) (Ljubešić et al., LREC 2016)
ACL