@
@
The
DeConverter is a language independent generator that provides a
framework for syntactic and morphological generation as well as
co-occurrence-based word selection for natural collocation. It can
deconvert UNL expressions into a variety of native languages, using a
number of linguistic data such as Word Dictionary, Grammatical Rules and
Co-occurrence Dictionary of each language.
The
DeConverter transforms the sentence represented by a UNL expression
– i.e., a set of binary relations –
into a directed hyper-graph structure called Node-net. The root
node of a Node-net is called Entry Node and represents the main
predicate of the sentence. The DeConverter applies generation rules to
every node in the Node-net and generates the word list in the target
language. In this process, the syntactic structure is determined by
applying Syntactic Rules. Morphemes
are similarly generated by applying Morphological Rules.
The
DeConverterfs generation ability is similar to that of a tuning
machine. It is capable of generating all types of sentences, applicable
to all languages. Co-occurrence Relations between words contribute to a
better word selection. This means it is possible to generate more
natural sentences by using Co-occurrence Relations.
@