# AGReE: A system for generating Automated Grammar Reading Exercises

arXiv: https://arxiv.org/abs/2210.16302 · HTML: https://mlsanity.com/paper/2210.16302/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 23 references that are in the map.
- First posted on arXiv 28 Oct 2022.

## Builds on (most cited first, 3 of 3)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of Transformers](https://mlsanity.com/paper/2204.07237/) (2022)
- [GrammarTagger: A Multilingual, Minimally-Supervised Grammar Profiler for Language Education](https://mlsanity.com/paper/2104.03190/) (2021)

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

- [Generating Reading Comprehension Exercises with Large Language Models for Educational Applications](https://mlsanity.com/paper/2511.18860/) (2025)

## Abstract (arXiv)

We describe the AGReE system, which takes user-submitted passages as input and automatically generates grammar practice exercises that can be completed while reading. Multiple-choice practice items are generated for a variety of different grammar constructs: punctuation, articles, conjunctions, pronouns, prepositions, verbs, and nouns. We also conducted a large-scale human evaluation with around 4,500 multiple-choice practice items. We notice for 95% of items, a majority of raters out of five were able to identify the correct answer and for 85% of cases, raters agree that there is only one correct answer among the choices. Finally, the error analysis shows that raters made the most mistakes for punctuation and conjunctions.