As we work together to battle the coronavirus, we will continue to offer safe and secure online sessions . Even though our physical office is closed, in accordance with the guidelines recommended by CDC, we are working remotely and continuing to provide student, staff, and faculty assistance. We can be reached Monday-Friday 9am-4pm Mountain Standard Time at 520-621-3565 or by email – please refer to the iSchool Directory. Please allow up to 24 hours response time. Faculty and Adjuncts will respond as their schedules permit.
Get COVID-19 updates and information for the University of Arizona community.
“Assembling Information from Big Corpora by Focusing Machine Reading”, presented by Enrique Noriega
We propose a framework to teach an automated agent to learn how to search for multi-hop paths of relations between entities in large corpora. The method learns a policy for directing existing information retrieval and machine reading resources to focus on relevant regions of a corpus.
The approach formulates the learning problem as a Markov decision process with a state representation that encodes the dynamics of the search process and a reward structure that minimizes the number of documents that must be processed while still finding multi-hop paths.
We implement the framework with reinforcement learning and evaluate it on an open-domain dataset of search problems derived from a subset of English Wikipedia using a policy gradient actor-critic algorithm and a domain-specific dataset of search problems in the biomedical domain using a temporal-difference learning algorithm.
We show that deploying the focused reading framework with reinforcement learning finds policies that retrieve more multi-hop paths while processing fewer documents compared to several strong deterministic baseline implementations.