This course covers the basic theories and applications of language-based and interactive intelligent system using deep learning. Topics include distributional semantics with word embeddings, text classification, emotion recognition, sentiment analysis from text and speech, and language modeling, with neural networks and back-propagation, convolutional neural networks, and recurrent neural networks. We will also cover multi-linguality and multi-modality, end-to-end chatbots, and task-oriented dialogue systems. Students will learn about various natural language processing (NLP) tasks related to building interactive intelligent systems, how to design and build a deep learning model using PyTorch and Python, and the basics of software engineering. At the end of the course, students will work alone or in pairs to implement a deep learning model for various NLP research tasks, and describe their methods and results in a conference paper format. Successful groups will be able to submit their papers to an international conference.