ABSTRACT

This chapter introduces semantic content analysis, a methodology whose vehicle is automatic recognition and classification of instances in the knowledge representations of texts, or text models. Semantic content analysis differs from traditional content analysis because it operates on referentially integrated text models. Referential integration means that references to the same object or relation, which may appear in different sentences of a text, are resolved and represented as the same semantic node. Semantic perception is the process of mapping from a syntactic representation into a semantic representation. In RELATUS the construction of semantic representations from canonical grammatical relations and the original lexical items is informed by a theory of lexical-interpretive semantics. The RELATUS system reaches the level of eidetic representation and even somewhat beyond. RELATUS gains broad coverage and domain-independence from a bottom-up strategy that combines a general syntactic analysis with a constraint-posting reference system to create large, referentially integrated semantic representations.