@inproceedings{ingolfsdottir-etal-2023-byte,
title = "Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora",
author = "Ing{\'o}lfsd{\'o}ttir, Svanhv{\'\i}t Lilja and
Ragnarsson, Petur and
J{\'o}nsson, Haukur and
Simonarson, Haukur and
Thorsteinsson, Vilhjalmur and
Sn{\ae}bjarnarson, V{\'e}steinn",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.402",
doi = "10.18653/v1/2023.acl-long.402",
pages = "7299--7316",
abstract = "Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we compare the use of a common subword unit vocabulary and byte-level encoding. Initial synthetic training data is created using an error-generating pipeline, and used for finetuning two subword-level models and one byte-level model. Models are then finetuned further on hand-corrected error corpora, including texts written by children, university students, dyslexic and second-language writers, and evaluated over different error types and error origins. We show that a byte-level model enables higher correction quality than a subword approach, not only for simple spelling errors, but also for more complex semantic, stylistic and grammatical issues. In particular, initial training on synthetic corpora followed by finetuning on a relatively small parallel corpus of real-world errors helps the byte-level model correct a wide range of commonly occurring errors. Our experiments are run for the Icelandic language but should hold for other similar languages, and in particular to morphologically rich ones.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ingolfsdottir-etal-2023-byte">
<titleInfo>
<title>Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Svanhvít</namePart>
<namePart type="given">Lilja</namePart>
<namePart type="family">Ingólfsdóttir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petur</namePart>
<namePart type="family">Ragnarsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haukur</namePart>
<namePart type="family">Jónsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haukur</namePart>
<namePart type="family">Simonarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vilhjalmur</namePart>
<namePart type="family">Thorsteinsson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vésteinn</namePart>
<namePart type="family">Snæbjarnarson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we compare the use of a common subword unit vocabulary and byte-level encoding. Initial synthetic training data is created using an error-generating pipeline, and used for finetuning two subword-level models and one byte-level model. Models are then finetuned further on hand-corrected error corpora, including texts written by children, university students, dyslexic and second-language writers, and evaluated over different error types and error origins. We show that a byte-level model enables higher correction quality than a subword approach, not only for simple spelling errors, but also for more complex semantic, stylistic and grammatical issues. In particular, initial training on synthetic corpora followed by finetuning on a relatively small parallel corpus of real-world errors helps the byte-level model correct a wide range of commonly occurring errors. Our experiments are run for the Icelandic language but should hold for other similar languages, and in particular to morphologically rich ones.</abstract>
<identifier type="citekey">ingolfsdottir-etal-2023-byte</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.402</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.402</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>7299</start>
<end>7316</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora
%A Ingólfsdóttir, Svanhvít Lilja
%A Ragnarsson, Petur
%A Jónsson, Haukur
%A Simonarson, Haukur
%A Thorsteinsson, Vilhjalmur
%A Snæbjarnarson, Vésteinn
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ingolfsdottir-etal-2023-byte
%X Grammatical error correction (GEC) is the task of correcting typos, spelling, punctuation and grammatical issues in text. Approaching the problem as a sequence-to-sequence task, we compare the use of a common subword unit vocabulary and byte-level encoding. Initial synthetic training data is created using an error-generating pipeline, and used for finetuning two subword-level models and one byte-level model. Models are then finetuned further on hand-corrected error corpora, including texts written by children, university students, dyslexic and second-language writers, and evaluated over different error types and error origins. We show that a byte-level model enables higher correction quality than a subword approach, not only for simple spelling errors, but also for more complex semantic, stylistic and grammatical issues. In particular, initial training on synthetic corpora followed by finetuning on a relatively small parallel corpus of real-world errors helps the byte-level model correct a wide range of commonly occurring errors. Our experiments are run for the Icelandic language but should hold for other similar languages, and in particular to morphologically rich ones.
%R 10.18653/v1/2023.acl-long.402
%U https://aclanthology.org/2023.acl-long.402
%U https://doi.org/10.18653/v1/2023.acl-long.402
%P 7299-7316
Markdown (Informal)
[Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora](https://aclanthology.org/2023.acl-long.402) (Ingólfsdóttir et al., ACL 2023)
ACL
- Svanhvít Lilja Ingólfsdóttir, Petur Ragnarsson, Haukur Jónsson, Haukur Simonarson, Vilhjalmur Thorsteinsson, and Vésteinn Snæbjarnarson. 2023. Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 7299–7316, Toronto, Canada. Association for Computational Linguistics.