@inproceedings{ljubesic-etal-2016-corpus,
title = "Corpus-Based Diacritic Restoration for {S}outh {S}lavic Languages",
author = "Ljube{\v{s}}i{\'c}, Nikola and
Erjavec, Toma{\v{z}} and
Fi{\v{s}}er, Darja",
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/L16-1573",
pages = "3612--3616",
abstract = "In computer-mediated communication, Latin-based scripts users often omit diacritics when writing. Such text is typically easily understandable to humans but very difficult for computational processing because many words become ambiguous or unknown. Letter-level approaches to diacritic restoration generalise better and do not require a lot of training data but word-level approaches tend to yield better results. However, they typically rely on a lexicon which is an expensive resource, not covering non-standard forms, and often not available for less-resourced languages. In this paper we present diacritic restoration models that are trained on easy-to-acquire corpora. We test three different types of corpora (Wikipedia, general web, Twitter) for three South Slavic languages (Croatian, Serbian and Slovene) and evaluate them on two types of text: standard (Wikipedia) and non-standard (Twitter). The proposed approach considerably outperforms charlifter, so far the only open source tool available for this task. We make the best performing systems freely available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ljubesic-etal-2016-corpus">
<titleInfo>
<title>Corpus-Based Diacritic Restoration for South Slavic Languages</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>
<name type="personal">
<namePart type="given">Darja</namePart>
<namePart type="family">Fišer</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 computer-mediated communication, Latin-based scripts users often omit diacritics when writing. Such text is typically easily understandable to humans but very difficult for computational processing because many words become ambiguous or unknown. Letter-level approaches to diacritic restoration generalise better and do not require a lot of training data but word-level approaches tend to yield better results. However, they typically rely on a lexicon which is an expensive resource, not covering non-standard forms, and often not available for less-resourced languages. In this paper we present diacritic restoration models that are trained on easy-to-acquire corpora. We test three different types of corpora (Wikipedia, general web, Twitter) for three South Slavic languages (Croatian, Serbian and Slovene) and evaluate them on two types of text: standard (Wikipedia) and non-standard (Twitter). The proposed approach considerably outperforms charlifter, so far the only open source tool available for this task. We make the best performing systems freely available.</abstract>
<identifier type="citekey">ljubesic-etal-2016-corpus</identifier>
<location>
<url>https://aclanthology.org/L16-1573</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3612</start>
<end>3616</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Corpus-Based Diacritic Restoration for South Slavic Languages
%A Ljubešić, Nikola
%A Erjavec, Tomaž
%A Fišer, Darja
%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-corpus
%X In computer-mediated communication, Latin-based scripts users often omit diacritics when writing. Such text is typically easily understandable to humans but very difficult for computational processing because many words become ambiguous or unknown. Letter-level approaches to diacritic restoration generalise better and do not require a lot of training data but word-level approaches tend to yield better results. However, they typically rely on a lexicon which is an expensive resource, not covering non-standard forms, and often not available for less-resourced languages. In this paper we present diacritic restoration models that are trained on easy-to-acquire corpora. We test three different types of corpora (Wikipedia, general web, Twitter) for three South Slavic languages (Croatian, Serbian and Slovene) and evaluate them on two types of text: standard (Wikipedia) and non-standard (Twitter). The proposed approach considerably outperforms charlifter, so far the only open source tool available for this task. We make the best performing systems freely available.
%U https://aclanthology.org/L16-1573
%P 3612-3616
Markdown (Informal)
[Corpus-Based Diacritic Restoration for South Slavic Languages](https://aclanthology.org/L16-1573) (Ljubešić et al., LREC 2016)
ACL