Automatic Rule Acquisition for Spelling Correction

This paper describes a new approach to automatically learning linguistic knowledge for spelling correction. A major feature of this approach is the fact that the acquired knowledge is captured in a small set of easily understood rules, as opposed to a large set of opaque features and weights. A perspicuous representation is advantageous in order to best exploit human intuition to understand and improve upon the acquired knowledge of the system.

• Type: Conference
• Year: 1997
• Where: ICML
• Authors: Lidia Mangu, Eric Brill
• Keywords: Exploit Human Intuition, ICML 1997, Large Set, Linguistic Knowledge, Machine Learning