@inproceedings{marjou-2021-oteann,
title = "{OTEANN}: Estimating the Transparency of Orthographies with an Artificial Neural Network",
author = "Marjou, Xavier",
editor = {Vylomova, Ekaterina and
Salesky, Elizabeth and
Mielke, Sabrina and
Lapesa, Gabriella and
Kumar, Ritesh and
Hammarstr{\"o}m, Harald and
Vuli{\'c}, Ivan and
Korhonen, Anna and
Reichart, Roi and
Ponti, Edoardo Maria and
Cotterell, Ryan},
booktitle = "Proceedings of the Third Workshop on Computational Typology and Multilingual NLP",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sigtyp-1.1",
doi = "10.18653/v1/2021.sigtyp-1.1",
pages = "1--9",
abstract = "To transcribe spoken language to written medium, most alphabets enable an unambiguous sound-to-letter rule. However, some writing systems have distanced themselves from this simple concept and little work exists in Natural Language Processing (NLP) on measuring such distance. In this study, we use an Artificial Neural Network (ANN) model to evaluate the transparency between written words and their pronunciation, hence its name Orthographic Transparency Estimation with an ANN (OTEANN). Based on datasets derived from Wikimedia dictionaries, we trained and tested this model to score the percentage of false predictions in phoneme-to-grapheme and grapheme-to-phoneme translation tasks. The scores obtained on 17 orthographies were in line with the estimations of other studies. Interestingly, the model also provided insight into typical mistakes made by learners who only consider the phonemic rule in reading and writing.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marjou-2021-oteann">
<titleInfo>
<title>OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Marjou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Computational Typology and Multilingual NLP</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Vylomova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Mielke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harald</namePart>
<namePart type="family">Hammarström</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Vulić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roi</namePart>
<namePart type="family">Reichart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Edoardo</namePart>
<namePart type="given">Maria</namePart>
<namePart type="family">Ponti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To transcribe spoken language to written medium, most alphabets enable an unambiguous sound-to-letter rule. However, some writing systems have distanced themselves from this simple concept and little work exists in Natural Language Processing (NLP) on measuring such distance. In this study, we use an Artificial Neural Network (ANN) model to evaluate the transparency between written words and their pronunciation, hence its name Orthographic Transparency Estimation with an ANN (OTEANN). Based on datasets derived from Wikimedia dictionaries, we trained and tested this model to score the percentage of false predictions in phoneme-to-grapheme and grapheme-to-phoneme translation tasks. The scores obtained on 17 orthographies were in line with the estimations of other studies. Interestingly, the model also provided insight into typical mistakes made by learners who only consider the phonemic rule in reading and writing.</abstract>
<identifier type="citekey">marjou-2021-oteann</identifier>
<identifier type="doi">10.18653/v1/2021.sigtyp-1.1</identifier>
<location>
<url>https://aclanthology.org/2021.sigtyp-1.1</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1</start>
<end>9</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network
%A Marjou, Xavier
%Y Vylomova, Ekaterina
%Y Salesky, Elizabeth
%Y Mielke, Sabrina
%Y Lapesa, Gabriella
%Y Kumar, Ritesh
%Y Hammarström, Harald
%Y Vulić, Ivan
%Y Korhonen, Anna
%Y Reichart, Roi
%Y Ponti, Edoardo Maria
%Y Cotterell, Ryan
%S Proceedings of the Third Workshop on Computational Typology and Multilingual NLP
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F marjou-2021-oteann
%X To transcribe spoken language to written medium, most alphabets enable an unambiguous sound-to-letter rule. However, some writing systems have distanced themselves from this simple concept and little work exists in Natural Language Processing (NLP) on measuring such distance. In this study, we use an Artificial Neural Network (ANN) model to evaluate the transparency between written words and their pronunciation, hence its name Orthographic Transparency Estimation with an ANN (OTEANN). Based on datasets derived from Wikimedia dictionaries, we trained and tested this model to score the percentage of false predictions in phoneme-to-grapheme and grapheme-to-phoneme translation tasks. The scores obtained on 17 orthographies were in line with the estimations of other studies. Interestingly, the model also provided insight into typical mistakes made by learners who only consider the phonemic rule in reading and writing.
%R 10.18653/v1/2021.sigtyp-1.1
%U https://aclanthology.org/2021.sigtyp-1.1
%U https://doi.org/10.18653/v1/2021.sigtyp-1.1
%P 1-9
Markdown (Informal)
[OTEANN: Estimating the Transparency of Orthographies with an Artificial Neural Network](https://aclanthology.org/2021.sigtyp-1.1) (Marjou, SIGTYP 2021)
ACL