The following are some of our current sponsored research projects.
Retrieval-Enhanced Machine Learning Through an Information Retrieval Lens
This NSF-funded project is a collaboration with the CIIR and Carnegie Mellon University. This team will study Retrieval-Enhanced Machine Learning (REML) from an information retrieval (IR) perspective in which the retrieval component in REML is framed as a search engine capable of supporting multiple, independent predictive models, as opposed to a single predictive model as is the case in the majority of existing work.
CAREER: Explanation-based Optimization of Diversified Information Retrieval to Enhance AI Systems
This NSF-funded research project will focus on diverse and unbiased information access systems with the goal of making information seeking easier, more effective, and trustworthy for both day-to-day and power users. The project aims to enable users to obtain an interpretable, diverse, and unbiased set of alternative answers, viewpoints, subtopics, or aspects as required for various questions or tasks in information access systems, where each distinct answer or viewpoint is faithfully attributable to a set of evidence and supporting information sources.
CAREER: Enriching Conversational Information Retrieval via Mixed-Initiative Interactions
This NSF-funded research project addresses a key aspect of the future of search technology by providing access to information through natural language conversations. It aims to advance the state-of-the-art in conversational search by envisioning solutions that consider mixed-initiative interactions by studying (1) theoretical foundations for measuring mixed-initiative conversations; (2) models for clarifying the user's information needs; and (3) models for proactive informational contributions to ongoing conversations.
Athena: Learning-oriented Search With Personalized Learning Flows
This NSF-funded project is a collaboration with the CIIR and the University of North Carolina at Chapel Hill. The Athena project will develop technology called "search as learning," a set of search technologies that encourage and support learning rather than just simple document finding. The Athena work will extend the state of the art in text representation, neural approaches including attention techniques, query and topic modeling, contextual text summarization, and understanding human approaches to complex search activities.
