Exploring question representation and adaptation with neural networks

Neural networks have recently been intensively explored for machine comprehension and question answering. Core to the problems is the involvement of questions and hence the understanding of them - questions play a central role in machine comprehension, questions answering, and many other problems (e.g., information retrieval and query-based summarization). In this paper, we explore better question understanding and representation. First, we propose enriched question representation by encoding syntactic information with neural networks and filtering question content to different channels with filter banks. Second, in addition to providing a unified representation scheme for all questions, we differentiate different types of questions to provide the models with the flexibility of modelling different question groups. We propose an adaptation framework for this purpose. On the Stanford Question Answering Dataset (SQuAD), we show that our approaches improve a very competitive baseline to attain the state-of-the-art performance.