Concepedia

Publication | Closed Access

An unsupervised method for detecting grammatical errors

127

Citations

8

References

2000

Year

Abstract

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 errorrecognition system, ALEK, performs with about 80% precision and 20% recall.

References

YearCitations

Page 1