Grammatical Error Correction with (almost) no Linguistic Knowledge

Roman Grundkiewicz, Marcin Junczys-Dowmunt

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


In this work, we reinvestigate the classifier-based approach to article and preposition error correction going beyond linguistically motivated factors. We show that state-of-the-art results can be achieved without relying on a plethora of heuristic rules, complex feature engineering and advanced NLP tools. A proposed method for detecting spaces for article insertion is even more efficient than methods that use a parser. We are the first to propose and examine automatically trained word classes acquired by unsupervised learning as a substitution for commonly used part-of-speech tags. Our best models significantly outperform the top systems from CoNLL-2014 Shared Task in terms of article and preposition error correction.
Original languageEnglish
Title of host publicationProceedings of the 7th Language Technology Conference
Place of PublicationPoznan, Poland
Number of pages6
Publication statusPublished - Nov 2015


Dive into the research topics of 'Grammatical Error Correction with (almost) no Linguistic Knowledge'. Together they form a unique fingerprint.

Cite this