MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms

May 30, 2019 · Entered Twilight · 🏛 North American Chapter of the Association for Computational Linguistics

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: .DS_Store, LICENSE, README.md, _config.yml, css, data, graphics, gulpfile.js, html, img, index.html, js, leaderboard.html, mail, package-lock.json, package.json, scss, vendor

Authors Aida Amini, Saadia Gabriel, Peter Lin, Rik Koncel-Kedziorski, Yejin Choi, Hannaneh Hajishirzi arXiv ID 1905.13319 Category cs.CL: Computation & Language Citations 774 Venue North American Chapter of the Association for Computational Linguistics Repository https://github.com/math-qa/math-QA Last Checked 1 month ago

Abstract

We introduce a large-scale dataset of math word problems and an interpretable neural math problem solver that learns to map problems to operation programs. Due to annotation challenges, current datasets in this domain have been either relatively small in scale or did not offer precise operational annotations over diverse problem types. We introduce a new representation language to model precise operation programs corresponding to each math problem that aim to improve both the performance and the interpretability of the learned models. Using this representation language, our new dataset, MathQA, significantly enhances the AQuA dataset with fully-specified operational programs. We additionally introduce a neural sequence-to-program model enhanced with automatic problem categorization. Our experiments show improvements over competitive baselines in our MathQA as well as the AQuA dataset. The results are still significantly lower than human performance indicating that the dataset poses new challenges for future research. Our dataset is available at: https://math-qa.github.io/math-QA/