Extracting the Unknown from Long Math Problems

TL;DR

This paper introduces computational methods to identify unknown elements in long probability math problems, aiming to improve problem understanding and interpretability.

Contribution

It presents a novel approach for recognizing unknowns in complex math problem specifications, advancing the understanding of long mathematical problems.

Findings

Learning models perform strongly on the task

Results indicate potential for human-interpretable solutions

First step towards modular problem understanding

Abstract

In problem solving, understanding the problem that one seeks to solve is an essential initial step. In this paper, we propose computational methods for facilitating problem understanding through the task of recognizing the unknown in specifications of long Math problems. We focus on the topic of Probability. Our experimental results show that learning models yield strong results on the task, a promising first step towards human interpretable, modular approaches to understanding long Math problems.