This document discusses applying deep natural language processing techniques to various components of search systems, including query understanding, document ranking, auto-completion, and query suggestion. It describes challenges like data ambiguity, deep semantics, and online latency constraints. Several deep learning models are explored, like CNNs, LSTMs, CRFs, and BERT, for tasks like query tagging, intent classification, and neural ranking. Both offline and online experiments show potential gains from these techniques.