Attending to Mathematical Language with Transformers
share
Mathematical expressions were generated, evaluated and used to train neural network models based on the transformer architecture. The expressions and their targets were analyzed as a character-level sequence transduction task in which the encoder and decoder are built on attention mechanisms. Three models were trained to understand and evaluate symbolic variables and expressions in mathematics: (1) the self-attentive and feed-forward transformer without recurrence or convolution, (2) the universal transformer with recurrence, and (3) the adaptive universal transformer with recurrence and adaptive computation time. The models respectively achieved test accuracies as high as 76.1 and 83.9 cases inferred incorrectly, the results were very close to the targets. The models notably learned to add, subtract and multiply both positive and negative decimal numbers of variable digits assigned to symbolic variables.
READ FULL TEXT