Over the last ten years or so, the term " artificial intelligence " has come to the fore again and again. Advances in research into neural networks, an age-old technology, as well as increases in computing power and the mass of available data, have enabled a spectacular acceleration in the performance of artificial intelligence systems. At the heart of this revolution, automatic language processing (ALP) plays a central role. Long known through spelling correction and machine translation, this field of research dedicated to the analysis, generation and transformation of textual data has recently hit the headlines on several occasions, notably with the arrival of ChatGPT.
The aim of this lecture is to present the main current research areas in NLP. After an overview of what textual data are and how to represent them, we'll look at symbolic or probabilistic approaches, then turn to contemporary neural approaches and language models. We'll illustrate how these recent approaches have advanced NLP, taking a closer look at examples such as machine translation, but also at some of NLP's academic applications, particularly in linguistics. We will then look at conversational agents, in particular models such as ChatGPT and their challenges, and conclude with an overview of current research into multimodality, where text and speech or text and image are combined.