To enable meaning based search, computers have to store and compare meaning of user's search intentions and objects being searched. To address the key requirement of meaning compositionality, we present: design rationale; an algebraic theory; and a technique to represent composite meaning as a tensor which is amenable to efficient similarity computation.
—In this paper we present a fine grained parallel architecture that performs meaning comparison using vector cosine similarity (dot product). Meaning comparison assigns a similarity value to two objects (e.g. text documents) based on how similar their meanings (represented as two vectors) are to each other. The novelty of our design is the fine grained… (More)