@inproceedings{gershuni-pinter-2022-restoring,
title = "Restoring {H}ebrew Diacritics Without a Dictionary",
author = "Gershuni, Elazar and
Pinter, Yuval",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.75/",
doi = "10.18653/v1/2022.findings-naacl.75",
pages = "1010--1018",
abstract = "We demonstrate that it is feasible to accurately diacritize Hebrew script without any human-curated resources other than plain diacritized text. We present Nakdimon, a two-layer character-level LSTM, that performs on par with much more complicated curation-dependent systems, across a diverse array of modern Hebrew sources. The model is accompanied by a training set and a test set, collected from diverse sources."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gershuni-pinter-2022-restoring">
<titleInfo>
<title>Restoring Hebrew Diacritics Without a Dictionary</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elazar</namePart>
<namePart type="family">Gershuni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuval</namePart>
<namePart type="family">Pinter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We demonstrate that it is feasible to accurately diacritize Hebrew script without any human-curated resources other than plain diacritized text. We present Nakdimon, a two-layer character-level LSTM, that performs on par with much more complicated curation-dependent systems, across a diverse array of modern Hebrew sources. The model is accompanied by a training set and a test set, collected from diverse sources.</abstract>
<identifier type="citekey">gershuni-pinter-2022-restoring</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.75</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.75/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1010</start>
<end>1018</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Restoring Hebrew Diacritics Without a Dictionary
%A Gershuni, Elazar
%A Pinter, Yuval
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F gershuni-pinter-2022-restoring
%X We demonstrate that it is feasible to accurately diacritize Hebrew script without any human-curated resources other than plain diacritized text. We present Nakdimon, a two-layer character-level LSTM, that performs on par with much more complicated curation-dependent systems, across a diverse array of modern Hebrew sources. The model is accompanied by a training set and a test set, collected from diverse sources.
%R 10.18653/v1/2022.findings-naacl.75
%U https://aclanthology.org/2022.findings-naacl.75/
%U https://doi.org/10.18653/v1/2022.findings-naacl.75
%P 1010-1018
Markdown (Informal)
[Restoring Hebrew Diacritics Without a Dictionary](https://aclanthology.org/2022.findings-naacl.75/) (Gershuni & Pinter, Findings 2022)
ACL
- Elazar Gershuni and Yuval Pinter. 2022. Restoring Hebrew Diacritics Without a Dictionary. In Findings of the Association for Computational Linguistics: NAACL 2022, pages 1010–1018, Seattle, United States. Association for Computational Linguistics.