@inproceedings{csanady-lukacs-2022-dilated,
title = "Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration",
author = "Csan{\'a}dy, B{\'a}lint and
Luk{\'a}cs, Andr{\'a}s",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.452",
pages = "4253--4259",
abstract = "Diacritics restoration has become a ubiquitous task in the Latin-alphabet-based English-dominated Internet language environment. In this paper, we describe a small footprint 1D dilated convolution-based approach which operates on a character-level. We find that neural networks based on 1D dilated convolutions are competitive alternatives to solutions based on recurrent neural networks or linguistic modeling for the task of diacritics restoration. Our approach surpasses the performance of similarly sized models and is also competitive with larger models. A special feature of our solution is that it even runs locally in a web browser. We also provide a working example of this browser-based implementation. Our model is evaluated on different corpora, with emphasis on the Hungarian language. We performed comparative measurements about the generalization power of the model in relation to three Hungarian corpora. We also analyzed the errors to understand the limitation of corpus-based self-supervised training.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="csanady-lukacs-2022-dilated">
<titleInfo>
<title>Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bálint</namePart>
<namePart type="family">Csanády</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">András</namePart>
<namePart type="family">Lukács</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Diacritics restoration has become a ubiquitous task in the Latin-alphabet-based English-dominated Internet language environment. In this paper, we describe a small footprint 1D dilated convolution-based approach which operates on a character-level. We find that neural networks based on 1D dilated convolutions are competitive alternatives to solutions based on recurrent neural networks or linguistic modeling for the task of diacritics restoration. Our approach surpasses the performance of similarly sized models and is also competitive with larger models. A special feature of our solution is that it even runs locally in a web browser. We also provide a working example of this browser-based implementation. Our model is evaluated on different corpora, with emphasis on the Hungarian language. We performed comparative measurements about the generalization power of the model in relation to three Hungarian corpora. We also analyzed the errors to understand the limitation of corpus-based self-supervised training.</abstract>
<identifier type="citekey">csanady-lukacs-2022-dilated</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.452</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4253</start>
<end>4259</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration
%A Csanády, Bálint
%A Lukács, András
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F csanady-lukacs-2022-dilated
%X Diacritics restoration has become a ubiquitous task in the Latin-alphabet-based English-dominated Internet language environment. In this paper, we describe a small footprint 1D dilated convolution-based approach which operates on a character-level. We find that neural networks based on 1D dilated convolutions are competitive alternatives to solutions based on recurrent neural networks or linguistic modeling for the task of diacritics restoration. Our approach surpasses the performance of similarly sized models and is also competitive with larger models. A special feature of our solution is that it even runs locally in a web browser. We also provide a working example of this browser-based implementation. Our model is evaluated on different corpora, with emphasis on the Hungarian language. We performed comparative measurements about the generalization power of the model in relation to three Hungarian corpora. We also analyzed the errors to understand the limitation of corpus-based self-supervised training.
%U https://aclanthology.org/2022.lrec-1.452
%P 4253-4259
Markdown (Informal)
[Dilated Convolutional Neural Networks for Lightweight Diacritics Restoration](https://aclanthology.org/2022.lrec-1.452) (Csanády & Lukács, LREC 2022)
ACL