@inproceedings{vainikko-etal-2025-paragraph,
title = "Paragraph-level Error Correction and Explanation Generation: Case Study for {E}stonian",
author = "Vainikko, Martin and
Kamarik, Taavi and
Kert, Karina and
Liin, Krista and
Maine, Silvia and
Allkivi, Kais and
Kaivapalu, Annekatrin and
Fishel, Mark",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.bea-1.72/",
doi = "10.18653/v1/2025.bea-1.72",
pages = "953--967",
ISBN = "979-8-89176-270-1",
abstract = "We present a case study on building task-specific models for grammatical error correction and explanation generation tailored to learners of Estonian. Our approach handles whole paragraphs instead of sentences and leverages prompting proprietary large language models for generating synthetic training data, addressing the limited availability of error correction data and the complete absence of correction justification/explanation data in Estonian. We describe the chosen approach and pipeline and provide technical details for the experimental part. The final outcome is a set of open-weight models, which are released with a permissive license along with the generated synthetic error correction and explanation data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vainikko-etal-2025-paragraph">
<titleInfo>
<title>Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Vainikko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taavi</namePart>
<namePart type="family">Kamarik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karina</namePart>
<namePart type="family">Kert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Krista</namePart>
<namePart type="family">Liin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Silvia</namePart>
<namePart type="family">Maine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kais</namePart>
<namePart type="family">Allkivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annekatrin</namePart>
<namePart type="family">Kaivapalu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Fishel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>We present a case study on building task-specific models for grammatical error correction and explanation generation tailored to learners of Estonian. Our approach handles whole paragraphs instead of sentences and leverages prompting proprietary large language models for generating synthetic training data, addressing the limited availability of error correction data and the complete absence of correction justification/explanation data in Estonian. We describe the chosen approach and pipeline and provide technical details for the experimental part. The final outcome is a set of open-weight models, which are released with a permissive license along with the generated synthetic error correction and explanation data.</abstract>
<identifier type="citekey">vainikko-etal-2025-paragraph</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.72</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.72/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>953</start>
<end>967</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian
%A Vainikko, Martin
%A Kamarik, Taavi
%A Kert, Karina
%A Liin, Krista
%A Maine, Silvia
%A Allkivi, Kais
%A Kaivapalu, Annekatrin
%A Fishel, Mark
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F vainikko-etal-2025-paragraph
%X We present a case study on building task-specific models for grammatical error correction and explanation generation tailored to learners of Estonian. Our approach handles whole paragraphs instead of sentences and leverages prompting proprietary large language models for generating synthetic training data, addressing the limited availability of error correction data and the complete absence of correction justification/explanation data in Estonian. We describe the chosen approach and pipeline and provide technical details for the experimental part. The final outcome is a set of open-weight models, which are released with a permissive license along with the generated synthetic error correction and explanation data.
%R 10.18653/v1/2025.bea-1.72
%U https://aclanthology.org/2025.bea-1.72/
%U https://doi.org/10.18653/v1/2025.bea-1.72
%P 953-967
Markdown (Informal)
[Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian](https://aclanthology.org/2025.bea-1.72/) (Vainikko et al., BEA 2025)
ACL
- Martin Vainikko, Taavi Kamarik, Karina Kert, Krista Liin, Silvia Maine, Kais Allkivi, Annekatrin Kaivapalu, and Mark Fishel. 2025. Paragraph-level Error Correction and Explanation Generation: Case Study for Estonian. In Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025), pages 953–967, Vienna, Austria. Association for Computational Linguistics.