abstract = "We present a work in progress describing attribute
grammar approaches to Grammatical Evolution, which
allow us to encode context-sensitive and semantic
information. Performance of the different grammars
adopted are directly compared with a more traditional
GA representation on five instances of an NP-hard
knapsack problem. The results presented are
encouraging, demonstrating that Grammatical Evolution
in conjunction with alternative grammar representations
can provide an improvement over the standard
context-free grammar, and allow Grammatical Evolution
to drive a constraint based search.",
notes = "attributes (information, integers or list) can be
assigned to any symbol of the (recursive) grammar and
are defined (given meaning) by functions associated
with the grammar's productions. Attribute values from
child nodes (synthesised) or from parent nodes
(inherited). Information (constants) starts from root
(eg maxim weight) or leafs (weight of individual
items). Conditions (eg if(notinknapsack) and
if(usage+item < limit) ) are added to grammar
productions plus functions to calculate them (eg
limit=limit, usage=usage). Figure 1, page 8. pop=50,
gens<=2000.