# Solving Arithmetic Word Problems with Transformers and Preprocessing of Problem Text

arXiv: https://arxiv.org/abs/2106.00893 · HTML: https://mlsanity.com/paper/2106.00893/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 22 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 5 of 5)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Solving General Arithmetic Word Problems](https://mlsanity.com/paper/1608.01413/) (2016)
- [Unit Dependency Graph and its Application to Arithmetic Word Problem Solving](https://mlsanity.com/paper/1612.00969/) (2016)
- [Data-Driven Methods for Solving Algebra Word Problems](https://mlsanity.com/paper/1804.10718/) (2018)
- [Solving Arithmetic Word Problems Automatically Using Transformer and Unambiguous Representations](https://mlsanity.com/paper/1912.00871/) (2019)

## Built on by (most cited first, 7 of 7)

- [Length Generalization in Arithmetic Transformers](https://mlsanity.com/paper/2306.15400/) (2023)
- [Linear algebra with transformers](https://mlsanity.com/paper/2112.01898/) (2021)
- [Learning the greatest common divisor: explaining transformer predictions](https://mlsanity.com/paper/2308.15594/) (2023)
- [SALSA: Attacking Lattice Cryptography with Transformers](https://mlsanity.com/paper/2207.04785/) (2022)
- [Towards Tractable Mathematical Reasoning: Challenges, Strategies, and Opportunities for Solving Math Word Problems](https://mlsanity.com/paper/2111.05364/) (2021)
- [Salsa Fresca: Angular Embeddings and Pre-Training for ML Attacks on Learning With Errors](https://mlsanity.com/paper/2402.01082/) (2024)
- [Solving Math Word Problems Using Estimation Verification and Equation Generation](https://mlsanity.com/paper/2509.18565/) (2025)

## Abstract (arXiv)

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.