Abstract There is a tremendous amount of variation in the acoustic properties of speech categories. A well-known example of this is the acoustic-phonetic variability found between talkers: different talkers will use the same acoustic pattern[…]
Abstract Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is[…]
Abstract Understanding the ways in which information flows through social networks is important for questions of influence–including tracking the spread of cultural trends and disinformation and measuring shifts in public opinion. Much work in this[…]
Abstract Many applications of natural language processing need to understand text from the rich context in which it occurs and present information in a new context. Interpreting the rich context of a sentence, either conversation[…]
Abstract Movie analysis is an umbrella term for many tasks aiming to automatically interpret, extract, and summarize the content of a movie. Potential applications include generating shorter versions of scripts to help with the decision[…]
Abstract Our world faces increasingly complex challenges: we destabilized the climate, haven’t beaten all diseases, and haven’t spread the values of democracy and freedom to large parts of the globe, where violence and riots reign[…]
Abstract This is a two-part seminar. The first part will be dedicated to discussing how we can apply bayesian approaches to model comparison in NLP (and also ML in general), the drawbacks and limitations of[…]
