Conventional and associative memory approaches to automatic spelling correction

 
This item is provided by the institution :
Technological Educational Institute of Athens
Repository :
Ypatia - Institutional Repository
see the original item page
in the repository's web site and access all digital files if the item*
share




1992 (EN)
Conventional and associative memory approaches to automatic spelling correction (EN)

Βασιλάς, Νικόλαος (EL)
Cherkassky, Vladimir (EN)
Wechsler, Harry (EN)
Brodt, Gregory L. (EN)

Τεχνολογικό Εκπαιδευτικό Ίδρυμα Αθήνας. Σχολή Τεχνολογικών Εφαρμογών. Τμήμα Μηχανικών Πληροφορικής Τ.Ε. (EL)

This paper reviews conventional and emerging associative-memory approaches to robust 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. Based on several recent ad hoc models for associative spelling checkers a generic model is proposed that incorporates powerful N-gram encoding for word representation and supervised-learning associative memories. Recent research on associative spelling checkers is summarized and some original results are presented. It is concluded that many neural network models do not provide a practically 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. (EN)

journalArticle

ισχυρή ανάκτηση δεδομένων (EN)
Associative storage (EN)
ορθογράφος (EN)
Neural networks (EN)
νευρωνικά δίκτυα (EN)
spelling checkers (EN)
string matching (EN)
Συνειρμική μνήμη (EN)
Ταύτιση (EN)
robust data retrieval (EN)

ΤΕΙ Αθήνας (EL)
Technological Educational Institute of Athens (EN)

Engineering Applications of Artificial Intelligence (EN)

English

1992-05

DOI: 10.1016/0952-1976(92)90006-6

Elsevier (EN)



*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)