@inproceedings{tufis-irimia-2006-roco,
title = "{R}o{C}o-News: A Hand Validated Journalistic Corpus of {R}omanian",
author = "Tufi{\c{s}}, Dan and
Irimia, Elena",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/451_pdf.pdf",
abstract = "The paper briefly describes the RoCo project and, in details, one of its first outcomes, the RoCo-News corpus. RoCo-News is a middle-sized journalistic corpus of Romanian, abundant in proper names, numerals and named entities. The initially raw text was previously segmented with MtSeg segmenter, then POS annotated with TNT tagger. RoCo-News was further lemmatized and validated. Because of limited human resources, time constraints and the dimension of the corpus, hand validation of each individual token was out of question. The validation stage required a coherent methodology for automatically identifying as many POS annotation and lemmatization errors as possible. The hand validation process was focused on these automatically spotted possible errors. This methodology relied on three main techniques for automatic detection of potential errors: 1. when lemmatizing the corpus, we extracted all the triples that were not found in the word-form lexicon; 2. we checked the correctness of POS annotation for closed class lexical categories, technique described by (Dickinson {\&} Meurers, 2003); 3. we exploited the hypothesis (Tufiº, 1999) according to which an accurately tagged text, re-tagged with the language model learnt from it (biased evaluation) should have more than 98{\%} tokens identically tagged.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tufis-irimia-2006-roco">
<titleInfo>
<title>RoCo-News: A Hand Validated Journalistic Corpus of Romanian</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">Elena</namePart>
<namePart type="family">Irimia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The paper briefly describes the RoCo project and, in details, one of its first outcomes, the RoCo-News corpus. RoCo-News is a middle-sized journalistic corpus of Romanian, abundant in proper names, numerals and named entities. The initially raw text was previously segmented with MtSeg segmenter, then POS annotated with TNT tagger. RoCo-News was further lemmatized and validated. Because of limited human resources, time constraints and the dimension of the corpus, hand validation of each individual token was out of question. The validation stage required a coherent methodology for automatically identifying as many POS annotation and lemmatization errors as possible. The hand validation process was focused on these automatically spotted possible errors. This methodology relied on three main techniques for automatic detection of potential errors: 1. when lemmatizing the corpus, we extracted all the triples that were not found in the word-form lexicon; 2. we checked the correctness of POS annotation for closed class lexical categories, technique described by (Dickinson & Meurers, 2003); 3. we exploited the hypothesis (Tufiº, 1999) according to which an accurately tagged text, re-tagged with the language model learnt from it (biased evaluation) should have more than 98% tokens identically tagged.</abstract>
<identifier type="citekey">tufis-irimia-2006-roco</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/451_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RoCo-News: A Hand Validated Journalistic Corpus of Romanian
%A Tufiş, Dan
%A Irimia, Elena
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F tufis-irimia-2006-roco
%X The paper briefly describes the RoCo project and, in details, one of its first outcomes, the RoCo-News corpus. RoCo-News is a middle-sized journalistic corpus of Romanian, abundant in proper names, numerals and named entities. The initially raw text was previously segmented with MtSeg segmenter, then POS annotated with TNT tagger. RoCo-News was further lemmatized and validated. Because of limited human resources, time constraints and the dimension of the corpus, hand validation of each individual token was out of question. The validation stage required a coherent methodology for automatically identifying as many POS annotation and lemmatization errors as possible. The hand validation process was focused on these automatically spotted possible errors. This methodology relied on three main techniques for automatic detection of potential errors: 1. when lemmatizing the corpus, we extracted all the triples that were not found in the word-form lexicon; 2. we checked the correctness of POS annotation for closed class lexical categories, technique described by (Dickinson & Meurers, 2003); 3. we exploited the hypothesis (Tufiº, 1999) according to which an accurately tagged text, re-tagged with the language model learnt from it (biased evaluation) should have more than 98% tokens identically tagged.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/451_pdf.pdf
Markdown (Informal)
[RoCo-News: A Hand Validated Journalistic Corpus of Romanian](http://www.lrec-conf.org/proceedings/lrec2006/pdf/451_pdf.pdf) (Tufiş & Irimia, LREC 2006)
ACL