Spelling checkers,spelling correctors and the misspellings of poor spellers
Information Processing and Management: an International Journal
Techniques for automatically correcting words in text
ACM Computing Surveys (CSUR)
A time-efficient, linear-space local similarity algorithm
Advances in Applied Mathematics
Internal and external evidence in the identification and semantic categorization of proper names
Corpus processing for lexical acquisition
Identifying unknown proper names in newswire text
Corpus processing for lexical acquisition
Predictive data mining: a practical guide
Predictive data mining: a practical guide
A technique for computer detection and correction of spelling errors
Communications of the ACM
Hierarchical and integrated error recovery based on bidirectional chart parsing technique
Hierarchical and integrated error recovery based on bidirectional chart parsing technique
Detecting and correcting morpho-syntactic errors in real texts
ANLC '92 Proceedings of the third conference on Applied natural language processing
Computational Linguistics - Special issue on ill-formed input
Integrated control of chart items for error repair
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 2
Towards a single proposal in spelling correction
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Spelling correction using context
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
Improving data driven wordclass tagging by system combination
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
| Hi-index | 0.00 |
This paper introduces a robust, portable system for categorizing unknown words. It is based on a multi- component architecture where each component is responsible for identifying one class of unknown words. The focus of this paper is the component that identifies spelling errors. The misspelling identifier uses a decision tree architecture to combine multiple types of evidence about the unknown word. The misspelling identifier is evaluated using data from live closed captions - a gem-e replete with a wide variety of unknown words.