@inproceedings{lill-sigga-mikkelsen-etal-2022-reusing,
title = "Reusing a Multi-lingual Setup to Bootstrap a Grammar Checker for a Very Low Resource Language without Data",
author = "Lill Sigga Mikkelsen, Inga and
Wiechetek, Linda and
A Pirinen, Flammie",
editor = "Moeller, Sarah and
Anastasopoulos, Antonios and
Arppe, Antti and
Chaudhary, Aditi and
Harrigan, Atticus and
Holden, Josh and
Lachler, Jordan and
Palmer, Alexis and
Rijhwani, Shruti and
Schwartz, Lane",
booktitle = "Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.computel-1.19/",
doi = "10.18653/v1/2022.computel-1.19",
pages = "149--158",
abstract = "Grammar checkers (GEC) are needed for digital language survival. Very low resource languages like Lule S{\'a}mi with less than 3,000 speakers need to hurry to build these tools, but do not have the big corpus data that are required for the construction of machine learning tools. We present a rule-based tool and a workflow where the work done for a related language can speed up the process. We use an existing grammar to infer rules for the new language, and we do not need a large gold corpus of annotated grammar errors, but a smaller corpus of regression tests is built while developing the tool. We present a test case for Lule S{\'a}mi reusing resources from North S{\'a}mi, show how we achieve a categorisation of the most frequent errors, and present a preliminary evaluation of the system. We hope this serves as an inspiration for small languages that need advanced tools in a limited amount of time, but do not have big data."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lill-sigga-mikkelsen-etal-2022-reusing">
<titleInfo>
<title>Reusing a Multi-lingual Setup to Bootstrap a Grammar Checker for a Very Low Resource Language without Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Inga</namePart>
<namePart type="family">Lill Sigga Mikkelsen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linda</namePart>
<namePart type="family">Wiechetek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flammie</namePart>
<namePart type="family">A Pirinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Moeller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonios</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antti</namePart>
<namePart type="family">Arppe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aditi</namePart>
<namePart type="family">Chaudhary</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atticus</namePart>
<namePart type="family">Harrigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josh</namePart>
<namePart type="family">Holden</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Lachler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shruti</namePart>
<namePart type="family">Rijhwani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lane</namePart>
<namePart type="family">Schwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammar checkers (GEC) are needed for digital language survival. Very low resource languages like Lule Sámi with less than 3,000 speakers need to hurry to build these tools, but do not have the big corpus data that are required for the construction of machine learning tools. We present a rule-based tool and a workflow where the work done for a related language can speed up the process. We use an existing grammar to infer rules for the new language, and we do not need a large gold corpus of annotated grammar errors, but a smaller corpus of regression tests is built while developing the tool. We present a test case for Lule Sámi reusing resources from North Sámi, show how we achieve a categorisation of the most frequent errors, and present a preliminary evaluation of the system. We hope this serves as an inspiration for small languages that need advanced tools in a limited amount of time, but do not have big data.</abstract>
<identifier type="citekey">lill-sigga-mikkelsen-etal-2022-reusing</identifier>
<identifier type="doi">10.18653/v1/2022.computel-1.19</identifier>
<location>
<url>https://aclanthology.org/2022.computel-1.19/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>149</start>
<end>158</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reusing a Multi-lingual Setup to Bootstrap a Grammar Checker for a Very Low Resource Language without Data
%A Lill Sigga Mikkelsen, Inga
%A Wiechetek, Linda
%A A Pirinen, Flammie
%Y Moeller, Sarah
%Y Anastasopoulos, Antonios
%Y Arppe, Antti
%Y Chaudhary, Aditi
%Y Harrigan, Atticus
%Y Holden, Josh
%Y Lachler, Jordan
%Y Palmer, Alexis
%Y Rijhwani, Shruti
%Y Schwartz, Lane
%S Proceedings of the Fifth Workshop on the Use of Computational Methods in the Study of Endangered Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F lill-sigga-mikkelsen-etal-2022-reusing
%X Grammar checkers (GEC) are needed for digital language survival. Very low resource languages like Lule Sámi with less than 3,000 speakers need to hurry to build these tools, but do not have the big corpus data that are required for the construction of machine learning tools. We present a rule-based tool and a workflow where the work done for a related language can speed up the process. We use an existing grammar to infer rules for the new language, and we do not need a large gold corpus of annotated grammar errors, but a smaller corpus of regression tests is built while developing the tool. We present a test case for Lule Sámi reusing resources from North Sámi, show how we achieve a categorisation of the most frequent errors, and present a preliminary evaluation of the system. We hope this serves as an inspiration for small languages that need advanced tools in a limited amount of time, but do not have big data.
%R 10.18653/v1/2022.computel-1.19
%U https://aclanthology.org/2022.computel-1.19/
%U https://doi.org/10.18653/v1/2022.computel-1.19
%P 149-158
Markdown (Informal)
[Reusing a Multi-lingual Setup to Bootstrap a Grammar Checker for a Very Low Resource Language without Data](https://aclanthology.org/2022.computel-1.19/) (Lill Sigga Mikkelsen et al., ComputEL 2022)
ACL