Capturing Greater Context for Question Generation
This addresses the challenge of automatic question generation for applications like dialogue systems and reading comprehension, though it appears incremental as it builds on existing sequence-to-sequence models.
The paper tackles the problem of generating realistic questions from long documents by incorporating interactions across multiple sentences, outperforming state-of-the-art methods on SQuAD, MS MARCO, and NewsQA datasets.
Automatic question generation can benefit many applications ranging from dialogue systems to reading comprehension. While questions are often asked with respect to long documents, there are many challenges with modeling such long documents. Many existing techniques generate questions by effectively looking at one sentence at a time, leading to questions that are easy and not reflective of the human process of question generation. Our goal is to incorporate interactions across multiple sentences to generate realistic questions for long documents. In order to link a broad document context to the target answer, we represent the relevant context via a multi-stage attention mechanism, which forms the foundation of a sequence to sequence model. We outperform state-of-the-art methods on question generation on three question-answering datasets -- SQuAD, MS MARCO and NewsQA.