Question Generation from Paragraphs: A Tale of Two Hierarchical Models
This work addresses a challenging task in NLP for generating questions from long text, but it is incremental as it builds on existing hierarchical and attention-based methods.
The authors tackled the problem of automatic question generation from paragraphs by proposing two hierarchical models, a BiLSTM with selective attention and a hierarchical Transformer, which outperformed flat models on SQuAD and MS MARCO datasets.
Automatic question generation from paragraphs is an important and challenging problem, particularly due to the long context from paragraphs. In this paper, we propose and study two hierarchical models for the task of question generation from paragraphs. Specifically, we propose (a) a novel hierarchical BiLSTM model with selective attention and (b) a novel hierarchical Transformer architecture, both of which learn hierarchical representations of paragraphs. We model a paragraph in terms of its constituent sentences, and a sentence in terms of its constituent words. While the introduction of the attention mechanism benefits the hierarchical BiLSTM model, the hierarchical Transformer, with its inherent attention and positional encoding mechanisms also performs better than flat transformer model. We conducted empirical evaluation on the widely used SQuAD and MS MARCO datasets using standard metrics. The results demonstrate the overall effectiveness of the hierarchical models over their flat counterparts. Qualitatively, our hierarchical models are able to generate fluent and relevant questions