The Details: Training and Validating Big Models on Big Data

In this video, David Mimno discusses some of the different choices one can make in training models and what their implications are for efficiency, scalability, and topic quality, using the MALLET topic modeling package. This presentation was recorded on November 3, 2012 at the Maryland Institute for Technology as part of the Topic Modeling Workshop, sponsored by the National Endowment of the Humanities and MITH, at the University of Maryland. Slides are available here.


About David Mimno

David Mimno is a postdoctoral researcher in the Computer Science department at Princeton. He received his PhD from the University of Massachusetts Amherst. He previously worked for an internet auction startup, the NLP group at the University of Sheffield, and the Perseus Project, a cultural heritage digital library. He has a particular interest in historical texts and languages. David is currently chief maintainer for the MALLET Machine Learning toolkit.