@inproceedings{katinskaia-yangarber-2024-gpt-3,
title = "{GPT}-3.5 for Grammatical Error Correction",
author = "Katinskaia, Anisia and
Yangarber, Roman",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.692",
pages = "7831--7843",
abstract = "This paper investigates the application of GPT-3.5 for Grammatical Error Correction (GEC) in multiple languages in several settings: zero-shot GEC, fine-tuning for GEC, and using GPT-3.5 to re-rank correction hypotheses generated by other GEC models. In the zero-shot setting, we conduct automatic evaluations of the corrections proposed by GPT-3.5 using several methods: estimating grammaticality with language models (LMs), the Scribendy test, and comparing the semantic embeddings of sentences. GPT-3.5 has a known tendency to over-correct erroneous sentences and propose alternative corrections. For several languages, such as Czech, German, Russian, Spanish, and Ukrainian, GPT-3.5 substantially alters the source sentences, including their semantics, which presents significant challenges for evaluation with reference-based metrics. For English, GPT-3.5 demonstrates high recall, generates fluent corrections, and generally preserves sentence semantics. However, human evaluation for both English and Russian reveals that, despite its strong error-detection capabilities, GPT-3.5 struggles with several error types, including punctuation mistakes, tense errors, syntactic dependencies between words, and lexical compatibility at the sentence level.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="katinskaia-yangarber-2024-gpt-3">
<titleInfo>
<title>GPT-3.5 for Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anisia</namePart>
<namePart type="family">Katinskaia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Yangarber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper investigates the application of GPT-3.5 for Grammatical Error Correction (GEC) in multiple languages in several settings: zero-shot GEC, fine-tuning for GEC, and using GPT-3.5 to re-rank correction hypotheses generated by other GEC models. In the zero-shot setting, we conduct automatic evaluations of the corrections proposed by GPT-3.5 using several methods: estimating grammaticality with language models (LMs), the Scribendy test, and comparing the semantic embeddings of sentences. GPT-3.5 has a known tendency to over-correct erroneous sentences and propose alternative corrections. For several languages, such as Czech, German, Russian, Spanish, and Ukrainian, GPT-3.5 substantially alters the source sentences, including their semantics, which presents significant challenges for evaluation with reference-based metrics. For English, GPT-3.5 demonstrates high recall, generates fluent corrections, and generally preserves sentence semantics. However, human evaluation for both English and Russian reveals that, despite its strong error-detection capabilities, GPT-3.5 struggles with several error types, including punctuation mistakes, tense errors, syntactic dependencies between words, and lexical compatibility at the sentence level.</abstract>
<identifier type="citekey">katinskaia-yangarber-2024-gpt-3</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.692</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>7831</start>
<end>7843</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GPT-3.5 for Grammatical Error Correction
%A Katinskaia, Anisia
%A Yangarber, Roman
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F katinskaia-yangarber-2024-gpt-3
%X This paper investigates the application of GPT-3.5 for Grammatical Error Correction (GEC) in multiple languages in several settings: zero-shot GEC, fine-tuning for GEC, and using GPT-3.5 to re-rank correction hypotheses generated by other GEC models. In the zero-shot setting, we conduct automatic evaluations of the corrections proposed by GPT-3.5 using several methods: estimating grammaticality with language models (LMs), the Scribendy test, and comparing the semantic embeddings of sentences. GPT-3.5 has a known tendency to over-correct erroneous sentences and propose alternative corrections. For several languages, such as Czech, German, Russian, Spanish, and Ukrainian, GPT-3.5 substantially alters the source sentences, including their semantics, which presents significant challenges for evaluation with reference-based metrics. For English, GPT-3.5 demonstrates high recall, generates fluent corrections, and generally preserves sentence semantics. However, human evaluation for both English and Russian reveals that, despite its strong error-detection capabilities, GPT-3.5 struggles with several error types, including punctuation mistakes, tense errors, syntactic dependencies between words, and lexical compatibility at the sentence level.
%U https://aclanthology.org/2024.lrec-main.692
%P 7831-7843
Markdown (Informal)
[GPT-3.5 for Grammatical Error Correction](https://aclanthology.org/2024.lrec-main.692) (Katinskaia & Yangarber, LREC-COLING 2024)
ACL
- Anisia Katinskaia and Roman Yangarber. 2024. GPT-3.5 for Grammatical Error Correction. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7831–7843, Torino, Italia. ELRA and ICCL.