Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

8-2007

Abstract

Grammar checking and correction comprise of the primary problems in the area of Natural Language Processing (NLP). Traditional approaches fall into two major categories: Rule based and Corpus based. While the former relies heavily on grammar rules the latter approach is statistical in nature. We provide a novel corpus based approach for grammar checking that uses the principles of an Artificial Immune System (AIS).We treat grammatical error as pathogens (in immunological terms) and build antibody detectors capable of detecting grammatical errors while allowing correct constructs to filter through. Our results show that it is possible to detect a range of grammatical errors. This method can prove extremely useful in applications like Intelligent Tutoring Systems (ITS) and general purpose grammar checkers.

Discipline

Artificial Intelligence and Robotics | Computer Sciences | English Language and Literature

Research Areas

Intelligent Systems and Optimization

Publication

Artificial Immune Systems: 6th International Conference, ICARIS, Santos, Brazil, August 26-29, Proceedings

Volume

4628

First Page

348

Last Page

357

ISBN

9783540739227

Identifier

10.1007/978-3-540-73922-7_30

Publisher

Springer Verlag

City or Country

Berlin

Additional URL

https://doi.org/10.1007/978-3-540-73922-7_30

Download

Share

COinS