Hal Daume III is a new Assistant Professor in Computer Science, with a joint appointment in Linguistics. He is primarily interested in the interface between natural language processing, computational linguistics and machine learning.
His work in statistical modeling spans multiple aspects of language processing, including structured prediction, Bayesian methods, domain adaptation, and linguistic typology. Recently, he has been particularly interested in methods that involve processing many (100+) languages simultaneously, using linguistic insights (particularly from typology) to constrain the space of solutions that learning algorithms try to explore. He has latent interests in document summarization, discourse theory and language evolution.