Natural language processing (NLP) is a subfield of artificial intelligence that focuses on enabling computers to understand and process human languages.In the last five years,we have witnessed the rapid development of NLP in tasks such as machine translation,question-answering,and machine reading comprehension based on deep leing and an enormous volume of annotated and unannotated data.In this paper,we will review the latest progress in the neural network-based NLP framework (neural NLP) from three perspectives:modeling,leing,and reasoning.In the modeling section,we will describe several fundamental neural network-based modeling paradigms,such as word embedding,sentence embedding,and sequence-to-sequence modeling,which are widely used in mod NLP engines.In the leing section,we will introduce widely used leing methods for NLP models,including supervised,semi-supervised,and unsupervised leing;multitask leing;transfer leing;and active leing.We view reasoning as a new and exciting direction for neural NLP,but it has yet to be well addressed.In the reasoning section,we will review reasoning mechanisms,including the knowledge,existing non-neural inference methods,and new neural inference methods.We emphasize the importance of reasoning in this paper because it is important for building interpretable and knowledgedriven neural NLP models to handle complex tasks.At the end of this paper,we will briefly outline our thoughts on the future directions of neural NLP.