Video of the presentation is available at: https://www.youtube.com/watch?v=sOLXOsiX0Qk
Here is a description of the event, from the announcement:
Professor Surden will discuss some current and future applications of machine-learning within law. Legal practice is thought to require advanced cognitive abilities, but such higher-order cognition remains outside the capability of current machine-learning technology. Is it possible then to automate certain legal tasks despite this technological limitation? In some contexts, the answer may be yes due to a core principle: tasks that are normally thought to require human intelligence can sometimes be automated through the use of non-intelligent computational techniques that employ heuristics, patterns, or proxies capable of producing useful, “intelligent” results. He will then explore automation in the context of legal tasks currently performed by attorneys, including predicting the outcomes of legal cases, finding hidden relationships in legal documents and data, electronic discovery, and the automated organization of documents.