# Extracting the Unknown from Long Math Problems

arXiv: https://arxiv.org/abs/2103.12048 · HTML: https://mlsanity.com/paper/2103.12048/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 33 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms](https://mlsanity.com/paper/1905.13319/) (2019)
- [The Web as a Knowledge-base for Answering Complex Questions](https://mlsanity.com/paper/1803.06643/) (2018)
- [Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation](https://mlsanity.com/paper/1905.08205/) (2019)
- [Break It Down: A Question Understanding Benchmark](https://mlsanity.com/paper/2001.11770/) (2020)
- [Multi-hop Reading Comprehension through Question Decomposition and Rescoring](https://mlsanity.com/paper/1906.02916/) (2019)
- [Learning to Compose Neural Networks for Question Answering](https://mlsanity.com/paper/1601.01705/) (2016)
- [Semi-supervised Question Retrieval with Gated Convolutions](https://mlsanity.com/paper/1512.05726/) (2015)
- [Neural Compositional Denotational Semantics for Question Answering](https://mlsanity.com/paper/1808.09942/) (2018)
- [Discovering Sound Concepts and Acoustic Relations In Text](https://mlsanity.com/paper/1609.07384/) (2016)
- [Word Embedding based Correlation Model for Question/Answer Matching](https://mlsanity.com/paper/1511.04646/) (2015)

## Abstract (arXiv)

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.