# Introducing MathQA -- A Math-Aware Question Answering System

arXiv: https://arxiv.org/abs/1907.01642 · HTML: https://mlsanity.com/paper/1907.01642/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Multi-lingual Evaluation of Code Generation Models](https://mlsanity.com/paper/2210.14868/) (2022)
- [Why is constrained neural language generation particularly challenging?](https://mlsanity.com/paper/2206.05395/) (2022)
- [LLMs with Industrial Lens: Deciphering the Challenges and Prospects -- A Survey](https://mlsanity.com/paper/2402.14558/) (2024)
- [GLUECons: A Generic Benchmark for Learning Under Constraints](https://mlsanity.com/paper/2302.10914/) (2023)
- [Divide & Conquer for Entailment-aware Multi-hop Evidence Retrieval](https://mlsanity.com/paper/2311.02616/) (2023)
- [Discovery and Recognition of Formula Concepts using Machine Learning](https://mlsanity.com/paper/2303.01994/) (2023)
- [Perturbation-based Active Learning for Question Answering](https://mlsanity.com/paper/2311.02345/) (2023)
- [VcLLM: Video Codecs are Secretly Tensor Codecs](https://mlsanity.com/paper/2407.00467/) (2024)

## Abstract (arXiv)

We present an open source math-aware Question Answering System based on Ask Platypus. Our system returns as a single mathematical formula for a natural language question in English or Hindi. This formulae originate from the knowledge-base Wikidata. We translate these formulae to computable data by integrating the calculation engine sympy into our system. This way, users can enter numeric values for the variables occurring in the formula. Moreover, the system loads numeric values for constants occurring in the formula from Wikidata. In a user study, our system outperformed a commercial computational mathematical knowledge engine by 13%. However, the performance of our system heavily depends on the size and quality of the formula data available in Wikidata. Since only a few items in Wikidata contained formulae when we started the project, we facilitated the import process by suggesting formula edits to Wikidata editors. With the simple heuristic that the first formula is significant for the article, 80% of the suggestions were correct.