@inproceedings{tufis-ceausu-2008-diac,
title = "{DIAC}+: a Professional Diacritics Recovering System",
author = "Tufi{\c{s}}, Dan and
Ceau{\c{s}}u, Alexandru",
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/54_paper.pdf",
abstract = "In languages that use diacritical characters, if these special signs are stripped-off from a word, the resulted string of characters may not exist in the language, and therefore its normative form is, in general, easy to recover. However, this is not always the case, as presence or absence of a diacritical sign attached to a base letter of a word which exists in both variants, may change its grammatical properties or even the meaning, making the recovery of the missing diacritics a difficult task, not only for a program but sometimes even for a human reader. We describe and evaluate an accurate knowledge-based system for automatic recovery of the missing diacritics in MS-Office documents written in Romanian. For the rare cases when the system is not able to make a reliable decision, it either provides the user a list of words with their recovery suggestions, or probabilistically chooses one of the possible changes, but leaves a trace (a highlighted comment) on each word the modification of which was uncertain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufis-ceausu-2008-diac">
<titleInfo>
<title>DIAC+: a Professional Diacritics Recovering System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Tufiş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandru</namePart>
<namePart type="family">Ceauşu</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 languages that use diacritical characters, if these special signs are stripped-off from a word, the resulted string of characters may not exist in the language, and therefore its normative form is, in general, easy to recover. However, this is not always the case, as presence or absence of a diacritical sign attached to a base letter of a word which exists in both variants, may change its grammatical properties or even the meaning, making the recovery of the missing diacritics a difficult task, not only for a program but sometimes even for a human reader. We describe and evaluate an accurate knowledge-based system for automatic recovery of the missing diacritics in MS-Office documents written in Romanian. For the rare cases when the system is not able to make a reliable decision, it either provides the user a list of words with their recovery suggestions, or probabilistically chooses one of the possible changes, but leaves a trace (a highlighted comment) on each word the modification of which was uncertain.</abstract>
<identifier type="citekey">tufis-ceausu-2008-diac</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/54_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DIAC+: a Professional Diacritics Recovering System
%A Tufiş, Dan
%A Ceauşu, Alexandru
%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 tufis-ceausu-2008-diac
%X In languages that use diacritical characters, if these special signs are stripped-off from a word, the resulted string of characters may not exist in the language, and therefore its normative form is, in general, easy to recover. However, this is not always the case, as presence or absence of a diacritical sign attached to a base letter of a word which exists in both variants, may change its grammatical properties or even the meaning, making the recovery of the missing diacritics a difficult task, not only for a program but sometimes even for a human reader. We describe and evaluate an accurate knowledge-based system for automatic recovery of the missing diacritics in MS-Office documents written in Romanian. For the rare cases when the system is not able to make a reliable decision, it either provides the user a list of words with their recovery suggestions, or probabilistically chooses one of the possible changes, but leaves a trace (a highlighted comment) on each word the modification of which was uncertain.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/54_paper.pdf
Markdown (Informal)
[DIAC+: a Professional Diacritics Recovering System](http://www.lrec-conf.org/proceedings/lrec2008/pdf/54_paper.pdf) (Tufiş & Ceauşu, LREC 2008)
ACL
- Dan Tufiş and Alexandru Ceauşu. 2008. DIAC+: a Professional Diacritics Recovering System. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).