@inproceedings{mehta-etal-2020-learnings,
title = "Learnings from Technological Interventions in a Low Resource Language: A Case-Study on {G}ondi",
author = "Mehta, Devansh and
Santy, Sebastin and
Mothilal, Ramaravind Kommiya and
Srivastava, Brij Mohan Lal and
Sharma, Alok and
Shukla, Anurag and
Prasad, Vishnu and
U, Venkanna and
Sharma, Amit and
Bali, Kalika",
booktitle = "Proceedings of the 12th Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.345",
pages = "2832--2838",
abstract = "The primary obstacle to developing technologies for low-resource languages is the lack of usable data. In this paper, we report the adaption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. In the process of data collection, we also help in its revival by expanding access to information in Gondi through the creation of linguistic resources that can be used by the community, such as a dictionary, children{'}s stories, an app with Gondi content from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform. At the end of these interventions, we collected a little less than 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts. The larger goal of the project is collecting enough data in Gondi to build and deploy viable language technologies like machine translation and speech to text systems that can help take the language onto the internet.",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mehta-etal-2020-learnings">
<titleInfo>
<title>Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi</title>
</titleInfo>
<name type="personal">
<namePart type="given">Devansh</namePart>
<namePart type="family">Mehta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastin</namePart>
<namePart type="family">Santy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramaravind</namePart>
<namePart type="given">Kommiya</namePart>
<namePart type="family">Mothilal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brij</namePart>
<namePart type="given">Mohan</namePart>
<namePart type="given">Lal</namePart>
<namePart type="family">Srivastava</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anurag</namePart>
<namePart type="family">Shukla</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishnu</namePart>
<namePart type="family">Prasad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Venkanna</namePart>
<namePart type="family">U</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amit</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-may</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Language Resources and Evaluation Conference</title>
</titleInfo>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>The primary obstacle to developing technologies for low-resource languages is the lack of usable data. In this paper, we report the adaption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. In the process of data collection, we also help in its revival by expanding access to information in Gondi through the creation of linguistic resources that can be used by the community, such as a dictionary, children’s stories, an app with Gondi content from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform. At the end of these interventions, we collected a little less than 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts. The larger goal of the project is collecting enough data in Gondi to build and deploy viable language technologies like machine translation and speech to text systems that can help take the language onto the internet.</abstract>
<identifier type="citekey">mehta-etal-2020-learnings</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.345</url>
</location>
<part>
<date>2020-may</date>
<extent unit="page">
<start>2832</start>
<end>2838</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi
%A Mehta, Devansh
%A Santy, Sebastin
%A Mothilal, Ramaravind Kommiya
%A Srivastava, Brij Mohan Lal
%A Sharma, Alok
%A Shukla, Anurag
%A Prasad, Vishnu
%A U, Venkanna
%A Sharma, Amit
%A Bali, Kalika
%S Proceedings of the 12th Language Resources and Evaluation Conference
%D 2020
%8 may
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F mehta-etal-2020-learnings
%X The primary obstacle to developing technologies for low-resource languages is the lack of usable data. In this paper, we report the adaption and deployment of 4 technology-driven methods of data collection for Gondi, a low-resource vulnerable language spoken by around 2.3 million tribal people in south and central India. In the process of data collection, we also help in its revival by expanding access to information in Gondi through the creation of linguistic resources that can be used by the community, such as a dictionary, children’s stories, an app with Gondi content from multiple sources and an Interactive Voice Response (IVR) based mass awareness platform. At the end of these interventions, we collected a little less than 12,000 translated words and/or sentences and identified more than 650 community members whose help can be solicited for future translation efforts. The larger goal of the project is collecting enough data in Gondi to build and deploy viable language technologies like machine translation and speech to text systems that can help take the language onto the internet.
%U https://aclanthology.org/2020.lrec-1.345
%P 2832-2838
Markdown (Informal)
[Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi](https://aclanthology.org/2020.lrec-1.345) (Mehta et al., LREC 2020)
ACL
- Devansh Mehta, Sebastin Santy, Ramaravind Kommiya Mothilal, Brij Mohan Lal Srivastava, Alok Sharma, Anurag Shukla, Vishnu Prasad, Venkanna U, Amit Sharma, and Kalika Bali. 2020. Learnings from Technological Interventions in a Low Resource Language: A Case-Study on Gondi. In Proceedings of the 12th Language Resources and Evaluation Conference, pages 2832–2838, Marseille, France. European Language Resources Association.