Systems and methods for structural indexing of natural language text

摘要: A structural natural language index is created by segmenting documents within a repository into text portions and extracting named entity, co-reference, lexical entries, structural-semantic relationships, speaker attribution meronymic derived features. constituent structure determined that contains the elements ordering information sufficient to reconstruct portion. functional of determined. set characterizing predicative triples are formed from applying linearization transfer rules. The structure, features combined form canonical Each added index. retrieved question classified determine type corresponding for generated. entries in searched matching relevant type. used conjunction with generation grammar create an answer. If fails, some or all entry returned as