Attending to Mathematical Language with Transformers
This work addresses the challenge of automated mathematical reasoning for AI systems, though it is incremental as it applies existing transformer architectures to a new domain.
The paper tackled the problem of evaluating mathematical expressions as a character-level sequence transduction task using transformer-based models, achieving test accuracies up to 84.9% with errors often differing by only one or two characters.
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%, 78.8% and 84.9% in evaluating the expressions to match the target values. For the cases inferred incorrectly, the results differed from the targets by only one or two characters. The models notably learned to add, subtract and multiply both positive and negative decimal numbers of variable digits assigned to symbolic variables.