Text2Math: End-to-end Parsing Text into Math Expressions
This addresses math-related problems like arithmetic word problems for users needing automated parsing, but it appears incremental as it builds on existing structured prediction approaches.
The authors tackled the problem of parsing text into math expressions by proposing Text2Math, an end-to-end model that predicts complete math expressions as tree structures, showing efficacy on benchmark datasets.
We propose Text2Math, a model for semantically parsing text into math expressions. The model can be used to solve different math related problems including arithmetic word problems and equation parsing problems. Unlike previous approaches, we tackle the problem from an end-to-end structured prediction perspective where our algorithm aims to predict the complete math expression at once as a tree structure, where minimal manual efforts are involved in the process. Empirical results on benchmark datasets demonstrate the efficacy of our approach.