A Crash Course in Automatic Grammatical Error Correction

Roman Grundkiewicz, Christopher Bryant, Mariano Felice

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Grammatical Error Correction (GEC) is the task of automatically detecting and correcting all types of errors in written text. Although most research has focused on correcting errors in the context of English as a Second Language (ESL), GEC can also be applied to other languages and native text. The main application of a GEC system is thus to assist humans with their writing. Academic and commercial interest in GEC has grown significantly since the Helping Our Own (HOO) and Conference on Natural Language Learning (CoNLL) shared tasks in 2011-14, and a record-breaking 24 teams took part in the recent Building Educational Applications (BEA) shared task. Given this interest, and the recent shift towards neural approaches, we believe the time is right to offer a tutorial on GEC for researchers who may be new to the field or who are interested in the current state of the art and future challenges. With this in mind, the main goal of this tutorial is not only to bring attendees up to speed with GEC in general, but also examine the development of neural-based GEC systems.
Original languageEnglish
Title of host publicationProceedings of the 28th International Conference on Computational Linguistics: Tutorial Abstracts
Place of PublicationBarcelona, Spain (Online)
PublisherInternational Committee for Computational Linguistics
Number of pages6
ISBN (Electronic)978-1-952148-30-9
Publication statusPublished - 12 Dec 2020
EventThe 28th International Conference on Computational Linguistics - Virtual conference
Duration: 8 Dec 202013 Dec 2020


ConferenceThe 28th International Conference on Computational Linguistics
Abbreviated titleCOLING 2020
CityVirtual conference
Internet address


Dive into the research topics of 'A Crash Course in Automatic Grammatical Error Correction'. Together they form a unique fingerprint.

Cite this