My primary research interests are natural language processing and machine learning, with the long-term goal of building intelligent machine learning systems with the human-level language comprehension ability to assist humans in an effective, interpretable, and robust way (Survey). In pursuit of this goal, I develop principled methodologies of powering the deep neural networks with massive linguistic, commonsense, and multimodal knowledge, in support of real-world application scenarios such as question answering and multi-turn dialogue.