You can’t suggest that?!
In this article, we study correction of spelling errors, specifically on how the spelling errors are made and how can we model them computationally in order to fix them. The article describes two different approaches to generating spelling correction suggestions for three Uralic languages: Estonian,...
Published in: | Nordlyd |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English Norwegian |
Published: |
Septentrio Academic Publishing
2022
|
Subjects: | |
Online Access: | https://doi.org/10.7557/12.6349 https://doaj.org/article/66fab39dfd704bbc974aa4e1b585c8fa |
id |
ftdoajarticles:oai:doaj.org/article:66fab39dfd704bbc974aa4e1b585c8fa |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:66fab39dfd704bbc974aa4e1b585c8fa 2023-05-15T17:40:07+02:00 You can’t suggest that?! Heiki-Jaan Kaalep Flammie Pirinen Sjur Moshagen 2022-08-01T00:00:00Z https://doi.org/10.7557/12.6349 https://doaj.org/article/66fab39dfd704bbc974aa4e1b585c8fa EN NO eng nor Septentrio Academic Publishing https://septentrio.uit.no/index.php/nordlyd/article/view/6349 https://doaj.org/toc/1503-8599 doi:10.7557/12.6349 1503-8599 https://doaj.org/article/66fab39dfd704bbc974aa4e1b585c8fa Nordlyd: Tromsø University Working Papers on Language & Linguistics, Vol 46, Iss 1 (2022) Spell-Checking rule-based fsa machine learning sami languages estonian Language. Linguistic theory. Comparative grammar P101-410 article 2022 ftdoajarticles https://doi.org/10.7557/12.6349 2022-12-30T20:03:56Z In this article, we study correction of spelling errors, specifically on how the spelling errors are made and how can we model them computationally in order to fix them. The article describes two different approaches to generating spelling correction suggestions for three Uralic languages: Estonian, North Sámi and South Sámi. The first approach of modelling spelling errors is rule-based, where experts write rules that describe the kind of errors are made, and these are compiled into finite-state automaton that models the errors. The second is data-based, where we show a machine learning algorithm a corpus of errors that humans have made, and it creates a neural network that can model the errors. Both approaches require collection of error corpora and understanding its contents; therefore we also describe the actual errors we have seen in detail. We find that while both approaches create error correction systems, with current resources the expert-build systems are still more reliable. Article in Journal/Newspaper North Sámi sami Sámi South Sámi Directory of Open Access Journals: DOAJ Articles Nordlyd 46 1 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English Norwegian |
topic |
Spell-Checking rule-based fsa machine learning sami languages estonian Language. Linguistic theory. Comparative grammar P101-410 |
spellingShingle |
Spell-Checking rule-based fsa machine learning sami languages estonian Language. Linguistic theory. Comparative grammar P101-410 Heiki-Jaan Kaalep Flammie Pirinen Sjur Moshagen You can’t suggest that?! |
topic_facet |
Spell-Checking rule-based fsa machine learning sami languages estonian Language. Linguistic theory. Comparative grammar P101-410 |
description |
In this article, we study correction of spelling errors, specifically on how the spelling errors are made and how can we model them computationally in order to fix them. The article describes two different approaches to generating spelling correction suggestions for three Uralic languages: Estonian, North Sámi and South Sámi. The first approach of modelling spelling errors is rule-based, where experts write rules that describe the kind of errors are made, and these are compiled into finite-state automaton that models the errors. The second is data-based, where we show a machine learning algorithm a corpus of errors that humans have made, and it creates a neural network that can model the errors. Both approaches require collection of error corpora and understanding its contents; therefore we also describe the actual errors we have seen in detail. We find that while both approaches create error correction systems, with current resources the expert-build systems are still more reliable. |
format |
Article in Journal/Newspaper |
author |
Heiki-Jaan Kaalep Flammie Pirinen Sjur Moshagen |
author_facet |
Heiki-Jaan Kaalep Flammie Pirinen Sjur Moshagen |
author_sort |
Heiki-Jaan Kaalep |
title |
You can’t suggest that?! |
title_short |
You can’t suggest that?! |
title_full |
You can’t suggest that?! |
title_fullStr |
You can’t suggest that?! |
title_full_unstemmed |
You can’t suggest that?! |
title_sort |
you can’t suggest that?! |
publisher |
Septentrio Academic Publishing |
publishDate |
2022 |
url |
https://doi.org/10.7557/12.6349 https://doaj.org/article/66fab39dfd704bbc974aa4e1b585c8fa |
genre |
North Sámi sami Sámi South Sámi |
genre_facet |
North Sámi sami Sámi South Sámi |
op_source |
Nordlyd: Tromsø University Working Papers on Language & Linguistics, Vol 46, Iss 1 (2022) |
op_relation |
https://septentrio.uit.no/index.php/nordlyd/article/view/6349 https://doaj.org/toc/1503-8599 doi:10.7557/12.6349 1503-8599 https://doaj.org/article/66fab39dfd704bbc974aa4e1b585c8fa |
op_doi |
https://doi.org/10.7557/12.6349 |
container_title |
Nordlyd |
container_volume |
46 |
container_issue |
1 |
_version_ |
1766140933153226752 |