A Transformer Architecture for Online Gesture Recognition of Mathematical Expressions
This work addresses the challenge of accurate and robust online gesture recognition for mathematical expressions, with potential applications in education and assistive technologies, though it is incremental in adapting Transformers to this domain.
The paper tackles the problem of recognizing mathematical expressions from online handwritten gestures by using a Transformer architecture to build expression trees, achieving 94% accuracy in generating valid postfix RPN tree representations.
The Transformer architecture is shown to provide a powerful framework as an end-to-end model for building expression trees from online handwritten gestures corresponding to glyph strokes. In particular, the attention mechanism was successfully used to encode, learn and enforce the underlying syntax of expressions creating latent representations that are correctly decoded to the exact mathematical expression tree, providing robustness to ablated inputs and unseen glyphs. For the first time, the encoder is fed with spatio-temporal data tokens potentially forming an infinitely large vocabulary, which finds applications beyond that of online gesture recognition. A new supervised dataset of online handwriting gestures is provided for training models on generic handwriting recognition tasks and a new metric is proposed for the evaluation of the syntactic correctness of the output expression trees. A small Transformer model suitable for edge inference was successfully trained to an average normalised Levenshtein accuracy of 94%, resulting in valid postfix RPN tree representation for 94% of predictions.