@inproceedings{wu-lowery-2006-hebrew,
title = "A {H}ebrew Tree Bank Based on Cantillation Marks",
author = "Wu, Andi and
Lowery, Kirk",
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/6_pdf.pdf",
abstract = "In the Masoretic text of the Hebrew Bible (HB), the cantillation marks function like a punctuation system that shows the division and subdivision of each verse, forming a tree structure which is similar to the prosodic tree in modern linguistics. However, in the Masoretic text, the structure is hidden in a complicated set of diacritic symbols and the rich information is accessible only to a few trained scholars. In order to make the structural information available to the general public and to automatic processing by the computer, we built a tree bank where the hierarchical structure of each HB verse is explicitly represented in XML format. We coded the punctuation system in a context-tree grammar which was then used by a CYK parser to automatically generate trees for the whole HB. The results show that (1) the CFG correctly encoded the annotation rules and (2) the annotation done by the Masoretes is highly consistent.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-lowery-2006-hebrew">
<titleInfo>
<title>A Hebrew Tree Bank Based on Cantillation Marks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Lowery</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>In the Masoretic text of the Hebrew Bible (HB), the cantillation marks function like a punctuation system that shows the division and subdivision of each verse, forming a tree structure which is similar to the prosodic tree in modern linguistics. However, in the Masoretic text, the structure is hidden in a complicated set of diacritic symbols and the rich information is accessible only to a few trained scholars. In order to make the structural information available to the general public and to automatic processing by the computer, we built a tree bank where the hierarchical structure of each HB verse is explicitly represented in XML format. We coded the punctuation system in a context-tree grammar which was then used by a CYK parser to automatically generate trees for the whole HB. The results show that (1) the CFG correctly encoded the annotation rules and (2) the annotation done by the Masoretes is highly consistent.</abstract>
<identifier type="citekey">wu-lowery-2006-hebrew</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/6_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Hebrew Tree Bank Based on Cantillation Marks
%A Wu, Andi
%A Lowery, Kirk
%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 wu-lowery-2006-hebrew
%X In the Masoretic text of the Hebrew Bible (HB), the cantillation marks function like a punctuation system that shows the division and subdivision of each verse, forming a tree structure which is similar to the prosodic tree in modern linguistics. However, in the Masoretic text, the structure is hidden in a complicated set of diacritic symbols and the rich information is accessible only to a few trained scholars. In order to make the structural information available to the general public and to automatic processing by the computer, we built a tree bank where the hierarchical structure of each HB verse is explicitly represented in XML format. We coded the punctuation system in a context-tree grammar which was then used by a CYK parser to automatically generate trees for the whole HB. The results show that (1) the CFG correctly encoded the annotation rules and (2) the annotation done by the Masoretes is highly consistent.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/6_pdf.pdf
Markdown (Informal)
[A Hebrew Tree Bank Based on Cantillation Marks](http://www.lrec-conf.org/proceedings/lrec2006/pdf/6_pdf.pdf) (Wu & Lowery, LREC 2006)
ACL
- Andi Wu and Kirk Lowery. 2006. A Hebrew Tree Bank Based on Cantillation Marks. In Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06), Genoa, Italy. European Language Resources Association (ELRA).