Conditions which affect our mental health often affect the way we use language; and treatment often involves linguistic interaction. This talk will present work on three related projects investigating the use of NLP techniques to help improve diagnosis and treatment for such conditions. We will look at clinical dialogue between patient and doctor or therapist, in cases involving schizophrenia, depression and dementia; in each case, we find that diagnostic information and/or important treatment outcomes are related to observable features of a patient's language and interaction with their conversational partner. We discuss the nature of these phenomena and the suitability and accuracy of NLP techniques for detecting them in dialogue.
Dr Matthew Purver is a Reader in Computational Linguistics in the School of Electronic Engineering and Computer Science at Queen Mary University of London. He is joint head of the Computational Linguistics Lab and deputy head of the Cognitive Science research group; He is also a member of the Centre for Intelligent Sensing and the Centre for Digital Music. Beyond that, he has co-founded Chatterbox Labs in 2011. His main research interest is in the computational semantics and pragmatics of dialogue - using the context of a conversation to build models of what people are actually talking about. Before arriving at QMUL in 2009, he worked in the Computational Semantics Lab at CSLI, Stanford, on projects building an automatic meeting-understanding system and a conversational dialogue system for cars. Prior to that he did his PhD at King's College London with Jonathan Ginzburg, looking at clarificational dialogue and what it means for dialogue systems; and his BA and MPhil at Cambridge where he was lucky enough to be supervised by Karen Spärck Jones. In between, he spent 8 years as an engineer in the field of active noise & vibration control, mostly with Ultra Electronics and Noise Cancellation Technologies.