@inproceedings{alhafni-etal-2023-advancements,
title = "Advancements in {A}rabic Grammatical Error Detection and Correction: An Empirical Investigation",
author = "Alhafni, Bashar and
Inoue, Go and
Khairallah, Christian and
Habash, Nizar",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.396/",
doi = "10.18653/v1/2023.emnlp-main.396",
pages = "6430--6448",
abstract = "Grammatical error correction (GEC) is a well-explored problem in English with many existing models and datasets. However, research on GEC in morphologically rich languages has been limited due to challenges such as data scarcity and language complexity. In this paper, we present the first results on Arabic GEC using two newly developed Transformer-based pretrained sequence-to-sequence models. We also define the task of multi-class Arabic grammatical error detection (GED) and present the first results on multi-class Arabic GED. We show that using GED information as auxiliary input in GEC models improves GEC performance across three datasets spanning different genres. Moreover, we also investigate the use of contextual morphological preprocessing in aiding GEC systems. Our models achieve SOTA results on two Arabic GEC shared task datasets and establish a strong benchmark on a recently created dataset. We make our code, data, and pretrained models publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alhafni-etal-2023-advancements">
<titleInfo>
<title>Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Go</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Khairallah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nizar</namePart>
<namePart type="family">Habash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatical error correction (GEC) is a well-explored problem in English with many existing models and datasets. However, research on GEC in morphologically rich languages has been limited due to challenges such as data scarcity and language complexity. In this paper, we present the first results on Arabic GEC using two newly developed Transformer-based pretrained sequence-to-sequence models. We also define the task of multi-class Arabic grammatical error detection (GED) and present the first results on multi-class Arabic GED. We show that using GED information as auxiliary input in GEC models improves GEC performance across three datasets spanning different genres. Moreover, we also investigate the use of contextual morphological preprocessing in aiding GEC systems. Our models achieve SOTA results on two Arabic GEC shared task datasets and establish a strong benchmark on a recently created dataset. We make our code, data, and pretrained models publicly available.</abstract>
<identifier type="citekey">alhafni-etal-2023-advancements</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.396</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.396/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6430</start>
<end>6448</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation
%A Alhafni, Bashar
%A Inoue, Go
%A Khairallah, Christian
%A Habash, Nizar
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F alhafni-etal-2023-advancements
%X Grammatical error correction (GEC) is a well-explored problem in English with many existing models and datasets. However, research on GEC in morphologically rich languages has been limited due to challenges such as data scarcity and language complexity. In this paper, we present the first results on Arabic GEC using two newly developed Transformer-based pretrained sequence-to-sequence models. We also define the task of multi-class Arabic grammatical error detection (GED) and present the first results on multi-class Arabic GED. We show that using GED information as auxiliary input in GEC models improves GEC performance across three datasets spanning different genres. Moreover, we also investigate the use of contextual morphological preprocessing in aiding GEC systems. Our models achieve SOTA results on two Arabic GEC shared task datasets and establish a strong benchmark on a recently created dataset. We make our code, data, and pretrained models publicly available.
%R 10.18653/v1/2023.emnlp-main.396
%U https://aclanthology.org/2023.emnlp-main.396/
%U https://doi.org/10.18653/v1/2023.emnlp-main.396
%P 6430-6448
Markdown (Informal)
[Advancements in Arabic Grammatical Error Detection and Correction: An Empirical Investigation](https://aclanthology.org/2023.emnlp-main.396/) (Alhafni et al., EMNLP 2023)
ACL