NLP / WIC Benchmark:

Still working on this. I recently completed the concept for English words into new Grammar categories.

There are:

Four main groups for Nouns, verbs/actions, and adjectives/modifiers. The groups are: Moving/living things, Analytical/laws/concepts, Logical subparts/binary actions, Light sense/stories/beautiful terms. 

Eight other groups for the remainder: Numeric Quantifier, Scale Quantifier, Person/Agent, Question/Interrogative, Time-spatial, Direction-spatial, Conjuction/sentence breakers, Exlamation/greet/grunt.

The Twelve groups are also encoded with present/future/past and precise/optimistic/explaining. All Present things are Precise, all Future things are Optimistic, all Past things are Explaining. 

Finally, all words must only be in one category only. 

The concept is speed over quality... but as there's nothing for virtual experiences/high speed scenarios between hard-coded dialogue trees and GPT-3, this will sit right inbetween.

There are 3500 words to individually convert over so will take until the new year to do as I'm also looking at Speech Recognition software.

Speech Recognition:

Speech Recognition software today uses Algorithms/Ngrams/NN's, is really slow (1-3 seconds response time) and uses a lot of power... The speed of the NLP is roughly 0.1ms to process a sentence, so if the speech recognition is fast then it's suitable for virtual enviroments even at a lower quality.

Combining the NLP with speech rec is as simple as writing phonemes next to each word in the dictionary. If the user is speaking via voice then the NLPs word-to-token search can be skipped, as the word is already found. 

One of the benefits if it works is that a responding chatbot can completely vary the response time to suit the situation, including interrupting the user, which adds another layer of humanness.