Multi-Task Learning with Language Modeling for Question Generation
This work addresses question generation for NLP applications, but it is incremental as it builds on existing attention-based pointer generator models.
The paper tackles answer-aware question generation by integrating language modeling as an auxiliary task in a hierarchical multi-task learning structure, achieving state-of-the-art results on SQuAD and MARCO datasets.
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.