A94-1029 graph structures is used to guide text understanding . Contextual roles are introduced
A83-1020 work appears to be approaching text understanding from a word oriented viewpoint
A92-1024 Understanding Control The control of the text understanding component of JASPER follows a
C82-1049 message-passing system for natural language text understanding . The application domain is the
A94-1029 of shallow semantics to guide text understanding . Navigation points are in general
A88-1018 reasoning into simple heuristics for text understanding , albeit ad hoc . Although this
C00-1012 process . In the absence of deep text understanding , this boils down to making extensive
C80-1076 behaviour of representing his text understanding . Embedding these rules into
A94-1029 automatic authoring . As a deep text understanding is not required , semantic interpretation
A88-1029 solve a subset of the problems of text understanding . The TICC 's output messages
C80-1056 whenever ambiguities occur in text understanding systems . 3 ) We may overlook
A94-1029 full text information retrieval , text understanding is a main activity . The problem
C80-1056 sentences . EXAM is an experimental text understanding system designed to deal with
A92-1024 Conclusions JASPER shows that text understanding technology has progressed to
C80-1056 this paper , is an experimental text understanding system designed to deal with
A88-1018 language-driven parsing is important for text understanding . Bottom-up strategies identify
A97-1054 in areas such as lexicography , text understanding and information extraction ,
C02-1141 an illustration , in sdrt for text understanding , there is the Axiom ( 1 ) for
C02-1156 realize FrameNet 's potential use in text understanding and inference ( Fillmore and
C02-1132 amount of labor needed to create text understanding systems , whether that labor
hide detail