@inproceedings{azar-etal-2020-thesaurus,
title = "A Thesaurus for Biblical {H}ebrew",
author = "Azar, Miriam and
Pahmer, Aliza and
Waxman, Joshua",
editor = "Sprugnoli, Rachele and
Passarotti, Marco",
booktitle = "Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/2020.lt4hala-1.10",
pages = "68--73",
abstract = "We built a thesaurus for Biblical Hebrew, with connections between roots based on phonetic, semantic, and distributional similarity. To this end, we apply established algorithms to find connections between headwords based on existing lexicons and other digital resources. For semantic similarity, we utilize the cosine-similarity of tf-idf vectors of English gloss text of Hebrew headwords from Ernest Klein{'}s A Comprehensive Etymological Dictionary of the Hebrew Language for Readers of English as well as to Brown-Driver-Brigg{'}s Hebrew Lexicon. For phonetic similarity, we digitize part of Matityahu Clark{'}s Etymological Dictionary of Biblical Hebrew, grouping Hebrew roots into phonemic classes, and establish phonetic relationships between headwords in Klein{'}s Dictionary. For distributional similarity, we consider the cosine similarity of PPMI vectors of Hebrew roots and also, in a somewhat novel approach, apply Word2Vec to a Biblical corpus reduced to its lexemes. The resulting resource is helpful to those trying to understand Biblical Hebrew, and also stands as a good basis for programs trying to process the Biblical text.",
language = "English",
ISBN = "979-10-95546-53-5",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="azar-etal-2020-thesaurus">
<titleInfo>
<title>A Thesaurus for Biblical Hebrew</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Azar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aliza</namePart>
<namePart type="family">Pahmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Waxman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rachele</namePart>
<namePart type="family">Sprugnoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Passarotti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-53-5</identifier>
</relatedItem>
<abstract>We built a thesaurus for Biblical Hebrew, with connections between roots based on phonetic, semantic, and distributional similarity. To this end, we apply established algorithms to find connections between headwords based on existing lexicons and other digital resources. For semantic similarity, we utilize the cosine-similarity of tf-idf vectors of English gloss text of Hebrew headwords from Ernest Klein’s A Comprehensive Etymological Dictionary of the Hebrew Language for Readers of English as well as to Brown-Driver-Brigg’s Hebrew Lexicon. For phonetic similarity, we digitize part of Matityahu Clark’s Etymological Dictionary of Biblical Hebrew, grouping Hebrew roots into phonemic classes, and establish phonetic relationships between headwords in Klein’s Dictionary. For distributional similarity, we consider the cosine similarity of PPMI vectors of Hebrew roots and also, in a somewhat novel approach, apply Word2Vec to a Biblical corpus reduced to its lexemes. The resulting resource is helpful to those trying to understand Biblical Hebrew, and also stands as a good basis for programs trying to process the Biblical text.</abstract>
<identifier type="citekey">azar-etal-2020-thesaurus</identifier>
<location>
<url>https://aclanthology.org/2020.lt4hala-1.10</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>68</start>
<end>73</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Thesaurus for Biblical Hebrew
%A Azar, Miriam
%A Pahmer, Aliza
%A Waxman, Joshua
%Y Sprugnoli, Rachele
%Y Passarotti, Marco
%S Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages
%D 2020
%8 May
%I European Language Resources Association (ELRA)
%C Marseille, France
%@ 979-10-95546-53-5
%G English
%F azar-etal-2020-thesaurus
%X We built a thesaurus for Biblical Hebrew, with connections between roots based on phonetic, semantic, and distributional similarity. To this end, we apply established algorithms to find connections between headwords based on existing lexicons and other digital resources. For semantic similarity, we utilize the cosine-similarity of tf-idf vectors of English gloss text of Hebrew headwords from Ernest Klein’s A Comprehensive Etymological Dictionary of the Hebrew Language for Readers of English as well as to Brown-Driver-Brigg’s Hebrew Lexicon. For phonetic similarity, we digitize part of Matityahu Clark’s Etymological Dictionary of Biblical Hebrew, grouping Hebrew roots into phonemic classes, and establish phonetic relationships between headwords in Klein’s Dictionary. For distributional similarity, we consider the cosine similarity of PPMI vectors of Hebrew roots and also, in a somewhat novel approach, apply Word2Vec to a Biblical corpus reduced to its lexemes. The resulting resource is helpful to those trying to understand Biblical Hebrew, and also stands as a good basis for programs trying to process the Biblical text.
%U https://aclanthology.org/2020.lt4hala-1.10
%P 68-73
Markdown (Informal)
[A Thesaurus for Biblical Hebrew](https://aclanthology.org/2020.lt4hala-1.10) (Azar et al., LT4HALA 2020)
ACL
- Miriam Azar, Aliza Pahmer, and Joshua Waxman. 2020. A Thesaurus for Biblical Hebrew. In Proceedings of LT4HALA 2020 - 1st Workshop on Language Technologies for Historical and Ancient Languages, pages 68–73, Marseille, France. European Language Resources Association (ELRA).