Conventional and associative memory-based spelling checkers

Vladimir S Cherkassky, Nikolaos Vassilas, Gregory L. Brodt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations


The authors review conventional and emerging neural approaches to fault-tolerant data retrieval when the input keyword and/or database itself may contain noise (errors). Spelling checking is used as a primary example to illustrate various approaches and to contrast the difference between conventional (algorithmic) techniques and research methods based on neural associative memories. Recent research on associative spelling checkers is summarized and some original results are presented. It is concluded that most neural models do not provide a viable solution for robust data retrieval, due to saturation and scaling problems. However, a combination of conventional and neural approaches is shown to have excellent error correction rates and low computational costs; hence, it can be a good choice for robust data retrieval in large databases.

Original languageEnglish (US)
Title of host publicationProc 2 Int IEEE Conf Tools Artif Intell
PublisherPubl by IEEE
Number of pages7
ISBN (Print)0818620846
StatePublished - 1990
EventProceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence - Herndon, VA, USA
Duration: Nov 6 1990Nov 9 1990

Publication series

NameProc 2 Int IEEE Conf Tools Artif Intell


OtherProceedings of the 2nd International IEEE Conference on Tools for Artificial Intelligence
CityHerndon, VA, USA


Dive into the research topics of 'Conventional and associative memory-based spelling checkers'. Together they form a unique fingerprint.

Cite this