Humans use language as a way to express their feelings and communicate with each other. Due to the rapid growth of unstructured electronic data over the last decade, Natural Language Processing (NLP) has become one of the most important technologies of this information age. Similarly, the ever-increasing amount of Electronic Health Record (EHR) clinical free text documents has urged the need to build novel clinical NLP solutions towards optimizing the patient outcomes across the care continuum. Recently, Deep Learning (DL) techniques have demonstrated superior performance over the traditional Machine Learning (ML) techniques for many different NLP tasks. DL models are able to automatically learn representations of data and thus, do not require any traditional domain-specific feature engineering. This talk will present a brief intuitive overview of how DL algorithms can be applied to solve NLP problems, followed by a discussion on various DL-driven clinical NLP applications developed in the Artificial Intelligence lab at Philips Research - such as diagnostic inferencing from unstructured clinical narratives, and clinical paraphrase generation.