Card-handling using hypertext editor can be a powerful methodology for generation of ideas or understanding
of complex problems. To support such activity, recognizing implicit structure in the arrangement of cards
would be useful. But, because the structures to be recognized are by nature ambiguous and highly dependent
on user-specific perception, it is difficult for conventional rule-based spatial parsing algorithm to achieve this
task. We propose techniques for building spatial parser suitable for finding such ambiguous structures based
on the mechanics of human perception. Moreover, our parser is adaptively customized to reflect a particular
user's preferences through an interactive suggestion process, supported by application of a genetic algorithm.