Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text

2021/06/02 by Kaden Griffith, Jugal Kalita, Griffith, Kaden +1 · 1 citation
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Mathematics, Computing, and Information Processing #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2106.00893

openalex publication_date 2021/06/02 · openalex created_date 2021/06/22 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Robust Understanding of Word Problems with Extraneous Information
• Data-Driven Methods for Solving Algebra Word Problems
• Solving General Arithmetic Word Problems

Cited by

• Solving Math Word Problems Using Estimation Verification and Equation Generation

Related

• Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations
• Solving Math Word Problems with Double-Decoder Transformer
• Attending to Mathematical Language with Transformers
• Transformers discover an elementary calculation system exploiting local attention and grid-like problem representation
• Techniques to Improve Neural Math Word Problem Solvers