@inproceedings{ljubesic-erjavec-2016-corpus,
title = "Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of {S}lovene",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Erjavec, Toma{\v{z}}",
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/L16-1242",
pages = "1527--1531",
abstract = "In this paper we present a tagger developed for inflectionally rich languages for which both a training corpus and a lexicon are available. We do not constrain the tagger by the lexicon entries, allowing both for lexicon incompleteness and noisiness. By using the lexicon indirectly through features we allow for known and unknown words to be tagged in the same manner. We test our tagger on Slovene data, obtaining a 25{\%} error reduction of the best previous results both on known and unknown words. Given that Slovene is, in comparison to some other Slavic languages, a well-resourced language, we perform experiments on the impact of token (corpus) vs. type (lexicon) supervision, obtaining useful insights in how to balance the effort of extending resources to yield better tagging results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-erjavec-2016-corpus">
<titleInfo>
<title>Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene</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">Tomaž</namePart>
<namePart type="family">Erjavec</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 a tagger developed for inflectionally rich languages for which both a training corpus and a lexicon are available. We do not constrain the tagger by the lexicon entries, allowing both for lexicon incompleteness and noisiness. By using the lexicon indirectly through features we allow for known and unknown words to be tagged in the same manner. We test our tagger on Slovene data, obtaining a 25% error reduction of the best previous results both on known and unknown words. Given that Slovene is, in comparison to some other Slavic languages, a well-resourced language, we perform experiments on the impact of token (corpus) vs. type (lexicon) supervision, obtaining useful insights in how to balance the effort of extending resources to yield better tagging results.</abstract>
<identifier type="citekey">ljubesic-erjavec-2016-corpus</identifier>
<location>
<url>https://aclanthology.org/L16-1242</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>1527</start>
<end>1531</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene
%A Ljubešić, Nikola
%A Erjavec, Tomaž
%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-erjavec-2016-corpus
%X In this paper we present a tagger developed for inflectionally rich languages for which both a training corpus and a lexicon are available. We do not constrain the tagger by the lexicon entries, allowing both for lexicon incompleteness and noisiness. By using the lexicon indirectly through features we allow for known and unknown words to be tagged in the same manner. We test our tagger on Slovene data, obtaining a 25% error reduction of the best previous results both on known and unknown words. Given that Slovene is, in comparison to some other Slavic languages, a well-resourced language, we perform experiments on the impact of token (corpus) vs. type (lexicon) supervision, obtaining useful insights in how to balance the effort of extending resources to yield better tagging results.
%U https://aclanthology.org/L16-1242
%P 1527-1531
Markdown (Informal)
[Corpus vs. Lexicon Supervision in Morphosyntactic Tagging: the Case of Slovene](https://aclanthology.org/L16-1242) (Ljubešić & Erjavec, LREC 2016)
ACL