Home > Events > CLIP Colloquium: Laura Dietz ( U New Hampshire)

CLIP Colloquium: Laura Dietz ( U New Hampshire)

Time: 
Wednesday, March 28, 2018 - 11:00 AM to 12:00 PM
Location: 
3258 A.V. Williams Building (AVW)

Title: Text, Entities, and Relevant Context for Complex Answer Retrieval

Abstract: We all turn towards Wikipedia with questions we want to know more about, but eventually find ourselves on the limit of its coverage. Instead of providing "ten blue links" as common in Web search, why not answer any web query with something that looks and feels like Wikipedia? This talk is about algorithms that automatically retrieve and identify relevant entities, relevant aspects of entities, and relevant relations. In combiantion, this does not only facilitate a semantic machine-understanding of text and entities, but enables predictive models of what is relevant information a user is looking for. While this contributes to many challenging applications, we detail these algorithms in the context of the TREC Complex Answer Retrieval shared task (http://trec-car.cs.unh.edu).

Bio: Laura Dietz is an assistant professor at the department of Computer Science at UNH with a focus on text-based machine learning and information retrieval.

Previously she was a Post-doctoral Research Scientist at the Data and Web Science Group of Mannheim University, working with Prof. Simone Paolo Ponzetto. Before that she was a Research Scientist at the Center for Intelligent Information Retrieval (CIIR) working with Bruce Croft at University of Massachusetts. Before that she did a post-doc with Andrew McCallum. She graduated from Max Planck Insititute for Informatics in Saarbruecken, Germany in January 2011.