@inproceedings{allkivi-metsoja-kippar-2023-spelling,
title = "Spelling Correction for {E}stonian Learner Language",
author = "Allkivi-Metsoja, Kais and
Kippar, Jaagup",
editor = {Alum{\"a}e, Tanel and
Fishel, Mark},
booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
month = may,
year = "2023",
address = "T{\'o}rshavn, Faroe Islands",
publisher = "University of Tartu Library",
url = "https://aclanthology.org/2023.nodalida-1.79/",
pages = "782--788",
abstract = "Second and foreign language (L2) learners often make specific spelling errors compared to native speakers. Language-independent spell-checking algorithms that rely on n-gram models can offer a simple solution for improving learner error detection and correction due to context-sensitivity. As the open-source speller previously available for Estonian is rule-based, our aim was to evaluate the performance of bi- and trigram-based statistical spelling correctors on an error-tagged set of A2{--}C1-level texts written by L2 learners of Estonian. The newly trained spell-checking models were compared to existing correction tools (open-source and commercial). Then, the best-performing Jamspell corrector was trained on various datasets to analyse their effect on the correction results."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="allkivi-metsoja-kippar-2023-spelling">
<titleInfo>
<title>Spelling Correction for Estonian Learner Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kais</namePart>
<namePart type="family">Allkivi-Metsoja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaagup</namePart>
<namePart type="family">Kippar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanel</namePart>
<namePart type="family">Alumäe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library</publisher>
<place>
<placeTerm type="text">Tórshavn, Faroe Islands</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Second and foreign language (L2) learners often make specific spelling errors compared to native speakers. Language-independent spell-checking algorithms that rely on n-gram models can offer a simple solution for improving learner error detection and correction due to context-sensitivity. As the open-source speller previously available for Estonian is rule-based, our aim was to evaluate the performance of bi- and trigram-based statistical spelling correctors on an error-tagged set of A2–C1-level texts written by L2 learners of Estonian. The newly trained spell-checking models were compared to existing correction tools (open-source and commercial). Then, the best-performing Jamspell corrector was trained on various datasets to analyse their effect on the correction results.</abstract>
<identifier type="citekey">allkivi-metsoja-kippar-2023-spelling</identifier>
<location>
<url>https://aclanthology.org/2023.nodalida-1.79/</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>782</start>
<end>788</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Spelling Correction for Estonian Learner Language
%A Allkivi-Metsoja, Kais
%A Kippar, Jaagup
%Y Alumäe, Tanel
%Y Fishel, Mark
%S Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)
%D 2023
%8 May
%I University of Tartu Library
%C Tórshavn, Faroe Islands
%F allkivi-metsoja-kippar-2023-spelling
%X Second and foreign language (L2) learners often make specific spelling errors compared to native speakers. Language-independent spell-checking algorithms that rely on n-gram models can offer a simple solution for improving learner error detection and correction due to context-sensitivity. As the open-source speller previously available for Estonian is rule-based, our aim was to evaluate the performance of bi- and trigram-based statistical spelling correctors on an error-tagged set of A2–C1-level texts written by L2 learners of Estonian. The newly trained spell-checking models were compared to existing correction tools (open-source and commercial). Then, the best-performing Jamspell corrector was trained on various datasets to analyse their effect on the correction results.
%U https://aclanthology.org/2023.nodalida-1.79/
%P 782-788
Markdown (Informal)
[Spelling Correction for Estonian Learner Language](https://aclanthology.org/2023.nodalida-1.79/) (Allkivi-Metsoja & Kippar, NoDaLiDa 2023)
ACL
- Kais Allkivi-Metsoja and Jaagup Kippar. 2023. Spelling Correction for Estonian Learner Language. In Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa), pages 782–788, Tórshavn, Faroe Islands. University of Tartu Library.