Sub-Symbolic Knowledge Representation for Evocative Chat-bots

The proposed work illustrates how “primitive concepts”can be automatically induced from a text corpus. The pri-mitive concepts are identified by the orthonormal axis of a“conceptual” space induced by a methodology inspired tothe Latent Semantic Analysis approach. The methodologyrepresents a natural language sentence by means of a setof rotations of an orthonormal basis in the “conceptual”space. The rotations, triggered by the sequence of wordscomposing the sentence and realized by means of Geomet-ric Algebra rotors, allow to highlight “conceptual” rela-tions that can arise among the primitive concepts.