Raymond Bem
January 27, 2021
NextApp Corporation
hyperlink to product…NextApp
The latest generation of NextApp word suggestion technology has arrived!
More Accurate – former reliance on rank-ordered lists results in poor accuracy, maturization of NLP (Natural Language Processing) techniques improve performance considerably
Faster – filtering logic means a smaller server footprint as well as faster response time given a language set
Highly respected Modified Kneser-Ney Smoothing (MKNS) improves upon traditional back-off search methods
Process considers and weights appropriately the word-facings after and before the phrase
Lower count phrase options draw insight from the quantity of completion and followup phrases
Weigths are calculated based on the frequency of 1 and 2 count phrases, discounting lower level (ngram) search results
These discounts reduce errors generally by reducing the effect of highly popular words (e.g., “and”)
The NextApp is quite simple, the user simply enters a word or phrase and clicks one button
Underneath, calibrated tables are built from samples of modern news, blog, and twitter language
A final set of weights is applied to the MKNS model probabilities to better surface infrequent phrases
The user is returned a list of word selections presented in graphical format – the best choice is clearly called out in the results
Distance (y-axis) between the chosen word and other options easily depict strength of selection
NextApp Corporation is very excited about this latest work
Applications include assisted typing for disabled persons, business inventory consolidation projects, as well as plagiarism detection
App can be found at this link…NextApp