@inproceedings{johny-etal-2021-finite,
title = "Finite-state script normalization and processing utilities: The {N}isaba {B}rahmic library",
author = "Johny, Cibu and
Wolf-Sonkin, Lawrence and
Gutkin, Alexander and
Roark, Brian",
editor = "Gkatzia, Dimitra and
Seddah, Djam{\'e}",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-demos.3/",
doi = "10.18653/v1/2021.eacl-demos.3",
pages = "14--23",
abstract = "This paper presents an open-source library for efficient low-level processing of ten major South Asian Brahmic scripts. The library provides a flexible and extensible framework for supporting crucial operations on Brahmic scripts, such as NFC, visual normalization, reversible transliteration, and validity checks, implemented in Python within a finite-state transducer formalism. We survey some common Brahmic script issues that may adversely affect the performance of downstream NLP tasks, and provide the rationale for finite-state design and system implementation details."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="johny-etal-2021-finite">
<titleInfo>
<title>Finite-state script normalization and processing utilities: The Nisaba Brahmic library</title>
</titleInfo>
<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">Lawrence</namePart>
<namePart type="family">Wolf-Sonkin</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>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitra</namePart>
<namePart type="family">Gkatzia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamé</namePart>
<namePart type="family">Seddah</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>This paper presents an open-source library for efficient low-level processing of ten major South Asian Brahmic scripts. The library provides a flexible and extensible framework for supporting crucial operations on Brahmic scripts, such as NFC, visual normalization, reversible transliteration, and validity checks, implemented in Python within a finite-state transducer formalism. We survey some common Brahmic script issues that may adversely affect the performance of downstream NLP tasks, and provide the rationale for finite-state design and system implementation details.</abstract>
<identifier type="citekey">johny-etal-2021-finite</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-demos.3</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-demos.3/</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>14</start>
<end>23</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Finite-state script normalization and processing utilities: The Nisaba Brahmic library
%A Johny, Cibu
%A Wolf-Sonkin, Lawrence
%A Gutkin, Alexander
%A Roark, Brian
%Y Gkatzia, Dimitra
%Y Seddah, Djamé
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F johny-etal-2021-finite
%X This paper presents an open-source library for efficient low-level processing of ten major South Asian Brahmic scripts. The library provides a flexible and extensible framework for supporting crucial operations on Brahmic scripts, such as NFC, visual normalization, reversible transliteration, and validity checks, implemented in Python within a finite-state transducer formalism. We survey some common Brahmic script issues that may adversely affect the performance of downstream NLP tasks, and provide the rationale for finite-state design and system implementation details.
%R 10.18653/v1/2021.eacl-demos.3
%U https://aclanthology.org/2021.eacl-demos.3/
%U https://doi.org/10.18653/v1/2021.eacl-demos.3
%P 14-23
Markdown (Informal)
[Finite-state script normalization and processing utilities: The Nisaba Brahmic library](https://aclanthology.org/2021.eacl-demos.3/) (Johny et al., EACL 2021)
ACL