Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering
This work addresses incremental improvements in neural QA systems for better handling of diverse questions.
The paper tackled improving question understanding in neural QA by incorporating syntactic information and modeling question types as an adaptation task, achieving better results on SQuAD over a baseline.
The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA). In this paper, we approach the problems by closely modelling questions in a neural network framework. We first introduce syntactic information to help encode questions. We then view and model different types of questions and the information shared among them as an adaptation task and proposed adaptation models for them. On the Stanford Question Answering Dataset (SQuAD), we show that these approaches can help attain better results over a competitive baseline.