Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text
This work addresses the problem of automated math problem-solving for educational or AI applications, showing incremental improvements in accuracy.
The paper tackled solving arithmetic word problems by using Transformer networks to translate them into arithmetic expressions, achieving accuracy improvements of over 20 percentage points on most datasets and up to 30% compared to previous state-of-the-art methods.
This paper outlines the use of Transformer networks trained to translate math word problems to equivalent arithmetic expressions in infix, prefix, and postfix notations. We compare results produced by many neural configurations and find that most configurations outperform previously reported approaches on three of four datasets with significant increases in accuracy of over 20 percentage points. The best neural approaches boost accuracy by 30% when compared to the previous state-of-the-art on some datasets.