# Multi-Task Learning with Language Modeling for Question Generation

arXiv: https://arxiv.org/abs/1908.11813 · HTML: https://mlsanity.com/paper/1908.11813/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Aug 2019.

## Built on by (most cited first, 10 of 10)

- [Multi-Task Learning in Natural Language Processing: An Overview](https://mlsanity.com/paper/2109.09138/) (2021)
- [Controllable Open-ended Question Generation with A New Question Type Ontology](https://mlsanity.com/paper/2107.00152/) (2021)
- [Recent Advances in Neural Text Generation: A Task-Agnostic Survey](https://mlsanity.com/paper/2203.03047/) (2022)
- [Towards Diverse and Effective Question-Answer Pair Generation from Children Storybooks](https://mlsanity.com/paper/2306.06605/) (2023)
- [Task Diversity Shortens the ICL Plateau](https://mlsanity.com/paper/2410.05448/) (2024)
- [Survey of Natural Language Processing for Education: Taxonomy, Systematic Review, and Future Trends](https://mlsanity.com/paper/2401.07518/) (2024)
- [Enhancing Question Generation with Commonsense Knowledge](https://mlsanity.com/paper/2106.10454/) (2021)
- [Consecutive Question Generation via Dynamic Multitask Learning](https://mlsanity.com/paper/2211.08850/) (2022)
- [Ask To The Point: Open-Domain Entity-Centric Question Generation](https://mlsanity.com/paper/2310.14126/) (2023)
- [Automating Turkish Educational Quiz Generation Using Large Language Models](https://mlsanity.com/paper/2406.03397/) (2024)

## Abstract (arXiv)

This paper explores the task of answer-aware questions generation. Based on the attention-based pointer generator model, we propose to incorporate an auxiliary task of language modeling to help question generation in a hierarchical multi-task learning structure. Our joint-learning model enables the encoder to learn a better representation of the input sequence, which will guide the decoder to generate more coherent and fluent questions. On both SQuAD and MARCO datasets, our multi-task learning model boosts the performance, achieving state-of-the-art results. Moreover, human evaluation further proves the high quality of our generated questions.