Paper: An Unsupervised Method For Detecting Grammatical Errors

ACL ID A00-2019
Title An Unsupervised Method For Detecting Grammatical Errors
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Main Conference
Year 2000
Authors

We present an unsupervised method for detecting grammatical errors by inferring negative evidence from edited textual corpora. The system was developed and tested using essay-length responses to prompts on the Test of English as a Foreign Language (TOEFL). The error- recognition system, ALEK, performs with about 80% precision and 20% recall.