@inproceedings{demirsahin-etal-2022-criteria,
title = "Criteria for Useful Automatic {R}omanization in {S}outh {A}sian Languages",
author = "Demirsahin, Isin and
Johny, Cibu and
Gutkin, Alexander and
Roark, Brian",
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-1.718",
pages = "6662--6673",
abstract = "This paper presents a number of possible criteria for systems that transliterate South Asian languages from their native scripts into the Latin script, a process known as romanization. These criteria are related to either fidelity to human linguistic behavior (pronunciation transparency, naturalness and conventionality) or processing utility for people (ease of input) as well as under-the-hood in systems (invertibility and stability across languages and scripts). When addressing these differing criteria several linguistic considerations, such as modeling of prominent phonological processes and their relation to orthography, need to be taken into account. We discuss these key linguistic details in the context of Brahmic scripts and languages that use them, such as Hindi and Malayalam. We then present the core features of several romanization algorithms, implemented in a finite state transducer (FST) formalism, that address differing criteria. Implementations of these algorithms have been released as part of the Nisaba finite-state script processing library.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="demirsahin-etal-2022-criteria">
<titleInfo>
<title>Criteria for Useful Automatic Romanization in South Asian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Isin</namePart>
<namePart type="family">Demirsahin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cibu</namePart>
<namePart type="family">Johny</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gutkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Roark</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>This paper presents a number of possible criteria for systems that transliterate South Asian languages from their native scripts into the Latin script, a process known as romanization. These criteria are related to either fidelity to human linguistic behavior (pronunciation transparency, naturalness and conventionality) or processing utility for people (ease of input) as well as under-the-hood in systems (invertibility and stability across languages and scripts). When addressing these differing criteria several linguistic considerations, such as modeling of prominent phonological processes and their relation to orthography, need to be taken into account. We discuss these key linguistic details in the context of Brahmic scripts and languages that use them, such as Hindi and Malayalam. We then present the core features of several romanization algorithms, implemented in a finite state transducer (FST) formalism, that address differing criteria. Implementations of these algorithms have been released as part of the Nisaba finite-state script processing library.</abstract>
<identifier type="citekey">demirsahin-etal-2022-criteria</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.718</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>6662</start>
<end>6673</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Criteria for Useful Automatic Romanization in South Asian Languages
%A Demirsahin, Isin
%A Johny, Cibu
%A Gutkin, Alexander
%A Roark, Brian
%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 demirsahin-etal-2022-criteria
%X This paper presents a number of possible criteria for systems that transliterate South Asian languages from their native scripts into the Latin script, a process known as romanization. These criteria are related to either fidelity to human linguistic behavior (pronunciation transparency, naturalness and conventionality) or processing utility for people (ease of input) as well as under-the-hood in systems (invertibility and stability across languages and scripts). When addressing these differing criteria several linguistic considerations, such as modeling of prominent phonological processes and their relation to orthography, need to be taken into account. We discuss these key linguistic details in the context of Brahmic scripts and languages that use them, such as Hindi and Malayalam. We then present the core features of several romanization algorithms, implemented in a finite state transducer (FST) formalism, that address differing criteria. Implementations of these algorithms have been released as part of the Nisaba finite-state script processing library.
%U https://aclanthology.org/2022.lrec-1.718
%P 6662-6673
Markdown (Informal)
[Criteria for Useful Automatic Romanization in South Asian Languages](https://aclanthology.org/2022.lrec-1.718) (Demirsahin et al., LREC 2022)
ACL