The objective of the project is to design a system that is able to generate context-wise reasonable and meaningful responses to open-domain conversation queries. In open-domain conversation generation, the retrieval-based methods and neural network generative models are two main approaches; there are also some recent research about improving the context consistency of conversation generation. In this project, we try to use context resolution model to complete the queries to include more information from context, and use ranking models to rank the candidates from the combination of retrieval-based generation and generative model, based on their relevance to both queries and context. We will also try to use generative adversarial network and reinforcement learning in generative models to make responses with higher qualities.