@inproceedings{madhani-etal-2023-aksharantar,
title = "Aksharantar: Open {I}ndic-language Transliteration datasets and models for the Next Billion Users",
author = "Madhani, Yash and
Parthan, Sushane and
Bedekar, Priyanka and
Nc, Gokul and
Khapra, Ruchi and
Kunchukuttan, Anoop and
Kumar, Pratyush and
Khapra, Mitesh",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.4/",
doi = "10.18653/v1/2023.findings-emnlp.4",
pages = "40--57",
abstract = "Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs. However, few training and evaluation sets are publicly available. We introduce Aksharantar, the largest publicly available transliteration dataset for Indian languages created by mining from monolingual and parallel corpora, as well as collecting data from human annotators. The dataset contains 26 million transliteration pairs for 21 Indic languages from 3 language families using 12 scripts. Aksharantar is 21 times larger than existing datasets and is the first publicly available dataset for 7 languages and 1 language family. We also introduce a test set of 103k word pairs for 19 languages that enables a fine-grained analysis of transliteration models on native origin words, foreign words, frequent words, and rare words. Using the training set, we trained IndicXlit, a multilingual transliteration model that improves accuracy by 15{\%} on the Dakshina test set, and establishes strong baselines on the Aksharantar testset introduced in this work. The models, mining scripts, transliteration guidelines, and datasets are available at https://github.com/AI4Bharat/IndicXlit under open-source licenses."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madhani-etal-2023-aksharantar">
<titleInfo>
<title>Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="family">Madhani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sushane</namePart>
<namePart type="family">Parthan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Priyanka</namePart>
<namePart type="family">Bedekar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokul</namePart>
<namePart type="family">Nc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruchi</namePart>
<namePart type="family">Khapra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Kunchukuttan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pratyush</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mitesh</namePart>
<namePart type="family">Khapra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs. However, few training and evaluation sets are publicly available. We introduce Aksharantar, the largest publicly available transliteration dataset for Indian languages created by mining from monolingual and parallel corpora, as well as collecting data from human annotators. The dataset contains 26 million transliteration pairs for 21 Indic languages from 3 language families using 12 scripts. Aksharantar is 21 times larger than existing datasets and is the first publicly available dataset for 7 languages and 1 language family. We also introduce a test set of 103k word pairs for 19 languages that enables a fine-grained analysis of transliteration models on native origin words, foreign words, frequent words, and rare words. Using the training set, we trained IndicXlit, a multilingual transliteration model that improves accuracy by 15% on the Dakshina test set, and establishes strong baselines on the Aksharantar testset introduced in this work. The models, mining scripts, transliteration guidelines, and datasets are available at https://github.com/AI4Bharat/IndicXlit under open-source licenses.</abstract>
<identifier type="citekey">madhani-etal-2023-aksharantar</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.4</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.4/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>40</start>
<end>57</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users
%A Madhani, Yash
%A Parthan, Sushane
%A Bedekar, Priyanka
%A Nc, Gokul
%A Khapra, Ruchi
%A Kunchukuttan, Anoop
%A Kumar, Pratyush
%A Khapra, Mitesh
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F madhani-etal-2023-aksharantar
%X Transliteration is very important in the Indian language context due to the usage of multiple scripts and the widespread use of romanized inputs. However, few training and evaluation sets are publicly available. We introduce Aksharantar, the largest publicly available transliteration dataset for Indian languages created by mining from monolingual and parallel corpora, as well as collecting data from human annotators. The dataset contains 26 million transliteration pairs for 21 Indic languages from 3 language families using 12 scripts. Aksharantar is 21 times larger than existing datasets and is the first publicly available dataset for 7 languages and 1 language family. We also introduce a test set of 103k word pairs for 19 languages that enables a fine-grained analysis of transliteration models on native origin words, foreign words, frequent words, and rare words. Using the training set, we trained IndicXlit, a multilingual transliteration model that improves accuracy by 15% on the Dakshina test set, and establishes strong baselines on the Aksharantar testset introduced in this work. The models, mining scripts, transliteration guidelines, and datasets are available at https://github.com/AI4Bharat/IndicXlit under open-source licenses.
%R 10.18653/v1/2023.findings-emnlp.4
%U https://aclanthology.org/2023.findings-emnlp.4/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.4
%P 40-57
Markdown (Informal)
[Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users](https://aclanthology.org/2023.findings-emnlp.4/) (Madhani et al., Findings 2023)
ACL