NEURAL NETWORK PATTERN FOR ENHANCING FUNCTIONALITY OF ELECTRONIC DICTIONARIES

Abstract

The value of a dictionary is traditionally considered to be proportional to its physical volume, measured in the number of entries. However, the amount of useful data varies depending on existing hypertextual links across a dictionary. Therefore, its utility might also be calculated as proportional to the number of useful links among its structural parts which can interact in a similar way as neurons do via synapse links, provided that the number of links turns out to be exponentially greater than the number of entries. Today’s lexicographic practice, as well as an experiment held by the author with his own developed onomasiological electronic dictionary of phraseological synonyms “IdeoPhrase”, appears to demonstrate that the main criterion for establishing links automatically is the repetition of each kind of signs (stylistic labels, graphical word, metalinguistic comments). Automatically generated hypertextual links can be used for finding out semantic relations of different types among lexemes (synonymic, antonymic and others), semantic equivalence or similarity among lexemes in different languages (which is close to automatic translation), as well as compiling a new dictionary. The fact that generated relation established by а computer constitute new useful knowledge which has not been directly input by the compiler, qualifies this algorithm as artificial intelligence engine.

Keywords

• dictionary
• onomasiology
• hypertextuality
• computational lexicography
• translation
• semantics