Online Gesture Recognition using Transformer and Natural Language Processing. (arXiv:2305.03407v1 [cs.CL])

The Transformer architecture is shown to provide a powerful machine
transduction framework for online handwritten gestures corresponding to glyph
strokes of natural language sentences. The attention mechanism is successfully
used to create latent representations of an end-to-end encoder-decoder model,
solving multi-level segmentation while also learning some language features and
syntax rules. The additional use of a large decoding space with some learned
Byte-Pair-Encoding (BPE) is shown to provide robustness to ablated inputs and
syntax rules. The encoder stack was directly …

and natural language processing architecture arxiv attention decoder encoder encoder-decoder features framework gesture recognition language language processing machine natural natural language natural language processing processing recognition segmentation transformer transformer architecture