We explore contemporary, data-driven techniques for solving math word problems over recent large-scale datasets. We show that well-tuned neural equation classifiers can outperform more sophisticated models such as sequence to sequence and self-attention across these datasets. Our error analysis indicates that, while fully data driven models show some promise, semantic and world knowledge is necessary for further advances.
@article{arxiv.1804.10718,
title = {Data-Driven Methods for Solving Algebra Word Problems},
author = {Benjamin Robaidek and Rik Koncel-Kedziorski and Hannaneh Hajishirzi},
journal= {arXiv preprint arXiv:1804.10718},
year = {2018}
}