Researchers and financial practitioners alike are attempting to find meaningful applications for the newest advents in the field of natural language processing (NLP). Although language modelling for stock trading is not novel, the landscape has changed significantly in recent years. With the improvements of computational power, data storage and algorithmic efficiency, we have more data and modelling capacity at our disposal than ever before. A natural consequence of these changes is the exponential growth of available data. There is a growing need for automating the data exploration and identification process for low-latency downstream applications requiring timely forecasting or decision making. This talk will discuss some of the new advances in NLP and their relevance to text-driven trading.