Text-based Question Answering from Information Retrieval and Deep Neural Network Perspectives: A Survey

Text-based Question Answering (QA) is a challenging task which aims at\nfinding short concrete answers for users' questions. This line of research has\nbeen widely studied with information retrieval techniques and has received\nincreasing attention in recent years by considering deep neural network\napproaches. Deep learning approaches, which are the main focus of this paper,\nprovide a powerful technique to learn multiple layers of representations and\ninteraction between questions and texts. In this paper, we provide a\ncomprehensive overview of different models proposed for the QA task, including\nboth traditional information retrieval perspective, and more recent deep neural\nnetwork perspective. We also introduce well-known datasets for the task and\npresent available results from the literature to have a comparison between\ndifferent techniques.\n