Comparison between Google S2R, Pribor\u2019s Combinatorial Magic and Pribor\u2019s CHE (Contextual Hyper-Embedding)<\/b><\/p>\n
This document presents the characteristics, divergences and synergies between three approaches: Google S2R, Pribor\u2019s Combinatorial Magic and Pribor\u2019s CHE (Contextual Hyper-Embedding).<\/p>\n
1. Google\u2019s S2R *<\/b><\/p>\n
\u201cS2R\u201d means Speech-to-Retrieval. It is a recent voice search architecture that Google is deploying, which bypasses the explicit speech \u2192 text transcription step to try to directly establish a match between the spoken audio and the information sought. The model relies on a dual encoder: one processes the audio, the other the candidate texts, in order to bring their vector representations closer together in the same semantic space.<\/p>\n
2. Pribor\u2019s Combinatorial Magic<\/a><\/b><\/p>\n Combinatorial Magic is a bijective, lossless and fixed-dimensional encoding of simple sentences into 4D or 5D vectors: three symbolic components (Subject, Verb, Object) plus a \u201cmeta\u201d register of 8 or 16 bits. It is distinguished by O(1) complexity, total absence of information loss, and perfect interpretability.<\/p>\n