@inproceedings{belkebir-habash-2021-automatic,
title = "Automatic Error Type Annotation for {A}rabic",
author = "Belkebir, Riadh and
Habash, Nizar",
editor = "Bisazza, Arianna and
Abend, Omri",
booktitle = "Proceedings of the 25th Conference on Computational Natural Language Learning",
month = nov,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.conll-1.47/",
doi = "10.18653/v1/2021.conll-1.47",
pages = "596--606",
abstract = "We present ARETA, an automatic error type annotation system for Modern Standard Arabic. We design ARETA to address Arabic`s morphological richness and orthographic ambiguity. We base our error taxonomy on the Arabic Learner Corpus (ALC) Error Tagset with some modifications. ARETA achieves a performance of 85.8{\%} (micro average F1 score) on a manually annotated blind test portion of ALC. We also demonstrate ARETA`s usability by applying it to a number of submissions from the QALB 2014 shared task for Arabic grammatical error correction. The resulting analyses give helpful insights on the strengths and weaknesses of different submissions, which is more useful than the opaque M2 scoring metrics used in the shared task. ARETA employs a large Arabic morphological analyzer, but is completely unsupervised otherwise. We make ARETA publicly available."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belkebir-habash-2021-automatic">
<titleInfo>
<title>Automatic Error Type Annotation for Arabic</title>
</titleInfo>
<name type="personal">
<namePart type="given">Riadh</namePart>
<namePart type="family">Belkebir</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>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Conference on Computational Natural Language Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arianna</namePart>
<namePart type="family">Bisazza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omri</namePart>
<namePart type="family">Abend</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present ARETA, an automatic error type annotation system for Modern Standard Arabic. We design ARETA to address Arabic‘s morphological richness and orthographic ambiguity. We base our error taxonomy on the Arabic Learner Corpus (ALC) Error Tagset with some modifications. ARETA achieves a performance of 85.8% (micro average F1 score) on a manually annotated blind test portion of ALC. We also demonstrate ARETA‘s usability by applying it to a number of submissions from the QALB 2014 shared task for Arabic grammatical error correction. The resulting analyses give helpful insights on the strengths and weaknesses of different submissions, which is more useful than the opaque M2 scoring metrics used in the shared task. ARETA employs a large Arabic morphological analyzer, but is completely unsupervised otherwise. We make ARETA publicly available.</abstract>
<identifier type="citekey">belkebir-habash-2021-automatic</identifier>
<identifier type="doi">10.18653/v1/2021.conll-1.47</identifier>
<location>
<url>https://aclanthology.org/2021.conll-1.47/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>596</start>
<end>606</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Error Type Annotation for Arabic
%A Belkebir, Riadh
%A Habash, Nizar
%Y Bisazza, Arianna
%Y Abend, Omri
%S Proceedings of the 25th Conference on Computational Natural Language Learning
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online
%F belkebir-habash-2021-automatic
%X We present ARETA, an automatic error type annotation system for Modern Standard Arabic. We design ARETA to address Arabic‘s morphological richness and orthographic ambiguity. We base our error taxonomy on the Arabic Learner Corpus (ALC) Error Tagset with some modifications. ARETA achieves a performance of 85.8% (micro average F1 score) on a manually annotated blind test portion of ALC. We also demonstrate ARETA‘s usability by applying it to a number of submissions from the QALB 2014 shared task for Arabic grammatical error correction. The resulting analyses give helpful insights on the strengths and weaknesses of different submissions, which is more useful than the opaque M2 scoring metrics used in the shared task. ARETA employs a large Arabic morphological analyzer, but is completely unsupervised otherwise. We make ARETA publicly available.
%R 10.18653/v1/2021.conll-1.47
%U https://aclanthology.org/2021.conll-1.47/
%U https://doi.org/10.18653/v1/2021.conll-1.47
%P 596-606
Markdown (Informal)
[Automatic Error Type Annotation for Arabic](https://aclanthology.org/2021.conll-1.47/) (Belkebir & Habash, CoNLL 2021)
ACL
- Riadh Belkebir and Nizar Habash. 2021. Automatic Error Type Annotation for Arabic. In Proceedings of the 25th Conference on Computational Natural Language Learning, pages 596–606, Online. Association for Computational Linguistics.