@inproceedings{adler-etal-2008-tagging,
title = "Tagging a {H}ebrew Corpus: the Case of Participles",
author = "Adler, Meni and
Netzer, Yael and
Goldberg, Yoav and
Gabay, David and
Elhadad, Michael",
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/802_paper.pdf",
abstract = "We report on an effort to build a corpus of Modern Hebrew tagged with part-of-speech and morphology. We designed a tagset specific to Hebrew while focusing on four aspects: the tagset should be consistent with common linguistic knowledge; there should be maximal agreement among taggers as to the tags assigned to maintain consistency; the tagset should be useful for machine taggers and learning algorithms; and the tagset should be effective for applications relying on the tags as input features. In this paper, we illustrate these issues by explaining our decision to introduce a tag for beinoni forms in Hebrew. We explain how this tag is defined, and how it helped us improve manual tagging accuracy to a high-level, while improving automatic tagging and helping in the task of syntactic chunking.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="adler-etal-2008-tagging">
<titleInfo>
<title>Tagging a Hebrew Corpus: the Case of Participles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meni</namePart>
<namePart type="family">Adler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yael</namePart>
<namePart type="family">Netzer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Gabay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Elhadad</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>We report on an effort to build a corpus of Modern Hebrew tagged with part-of-speech and morphology. We designed a tagset specific to Hebrew while focusing on four aspects: the tagset should be consistent with common linguistic knowledge; there should be maximal agreement among taggers as to the tags assigned to maintain consistency; the tagset should be useful for machine taggers and learning algorithms; and the tagset should be effective for applications relying on the tags as input features. In this paper, we illustrate these issues by explaining our decision to introduce a tag for beinoni forms in Hebrew. We explain how this tag is defined, and how it helped us improve manual tagging accuracy to a high-level, while improving automatic tagging and helping in the task of syntactic chunking.</abstract>
<identifier type="citekey">adler-etal-2008-tagging</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/802_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tagging a Hebrew Corpus: the Case of Participles
%A Adler, Meni
%A Netzer, Yael
%A Goldberg, Yoav
%A Gabay, David
%A Elhadad, Michael
%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 adler-etal-2008-tagging
%X We report on an effort to build a corpus of Modern Hebrew tagged with part-of-speech and morphology. We designed a tagset specific to Hebrew while focusing on four aspects: the tagset should be consistent with common linguistic knowledge; there should be maximal agreement among taggers as to the tags assigned to maintain consistency; the tagset should be useful for machine taggers and learning algorithms; and the tagset should be effective for applications relying on the tags as input features. In this paper, we illustrate these issues by explaining our decision to introduce a tag for beinoni forms in Hebrew. We explain how this tag is defined, and how it helped us improve manual tagging accuracy to a high-level, while improving automatic tagging and helping in the task of syntactic chunking.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/802_paper.pdf
Markdown (Informal)
[Tagging a Hebrew Corpus: the Case of Participles](http://www.lrec-conf.org/proceedings/lrec2008/pdf/802_paper.pdf) (Adler et al., LREC 2008)
ACL
- Meni Adler, Yael Netzer, Yoav Goldberg, David Gabay, and Michael Elhadad. 2008. Tagging a Hebrew Corpus: the Case of Participles. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).