Sentence Paraphrasing from a Conceptual Base A model of natural language based on an underlying language-free representation of meaning is described. A program based on this model is able to produce sentence paraphrases which demonstrate understanding with respect to a given context. This generator operates in conjunction with a natural language analyzer and a combined memory and inference model. In generating sentences from meaning structures, the program employs both the information retrieval and deduction capabilities of the memory model. The model encompasses several diverse classes of linguistic knowledge, which include: (1) executable tests of conceptual properties stored in discrimination nets; (2) information relating conceptual to syntactic roles, stored in a word-sense dictionary, and (3) surface grammatical knowledge, stored in a formal grammar. CACM February, 1975 Goldman, N. M. artificial intelligence, natural language processing, language generation, models of cognitive processes, semantic representation 3.42 3.60 3.65 CA750204 JB January 12, 1978 8:43 AM 1885 4 2795 2581 4 2795 2739 4 2795 2795 4 2795 2795 4 2795 2795 4 2795 2921 4 2795 3087 4 2795 1928 5 2795 1989 5 2795 2274 5 2795 2795 5 2795 2795 5 2795 2795 5 2795