# An Empirical Study of Finding Similar Exercises

arXiv: https://arxiv.org/abs/2111.08322 · HTML: https://mlsanity.com/paper/2111.08322/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 16 Nov 2021.

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

- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Multi-Task Deep Neural Networks for Natural Language Understanding](https://mlsanity.com/paper/1901.11504/) (2019)
- [QuesNet: A Unified Representation for Heterogeneous Test Questions](https://mlsanity.com/paper/1905.10949/) (2019)
- [Kappa Learning: A New Method for Measuring Similarity Between Educational Items Using Performance Data](https://mlsanity.com/paper/1812.08390/) (2018)

## Built on by (most cited first, 1 of 1)

- [From Robots to Books: An Introduction to Smart Applications of AI in Education (AIEd)](https://mlsanity.com/paper/2301.10026/) (2023)

## Abstract (arXiv)

Education artificial intelligence aims to profit tasks in the education domain such as intelligent test paper generation and consolidation exercises where the main technique behind is how to match the exercises, known as the finding similar exercises(FSE) problem. Most of these approaches emphasized their model abilities to represent the exercise, unfortunately there are still many challenges such as the scarcity of data, insufficient understanding of exercises and high label noises. We release a Chinese education pre-trained language model BERTEdu for the label-scarce dataset and introduce the exercise normalization to overcome the diversity of mathematical formulas and terms in exercise. We discover new auxiliary tasks in an innovative way depends on problem-solving ideas and propose a very effective MoE enhanced multi-task model for FSE task to attain better understanding of exercises. In addition, confidence learning was utilized to prune train-set and overcome high noises in labeling data. Experiments show that these methods proposed in this paper are very effective.