[PDF][PDF] Weakly-supervised acquisition of open-domain classes and class attributes from web documents and query logs
M Pasca, B Van Durme - Proceedings of acl-08: Hlt, 2008 - aclanthology.org
M Pasca, B Van Durme
Proceedings of acl-08: Hlt, 2008•aclanthology.orgA new approach to large-scale information extraction exploits both Web documents and
query logs to acquire thousands of opendomain classes of instances, along with relevant
sets of open-domain class attributes at precision levels previously obtained only on small-
scale, manually-assembled classes.
query logs to acquire thousands of opendomain classes of instances, along with relevant
sets of open-domain class attributes at precision levels previously obtained only on small-
scale, manually-assembled classes.
Abstract
A new approach to large-scale information extraction exploits both Web documents and query logs to acquire thousands of opendomain classes of instances, along with relevant sets of open-domain class attributes at precision levels previously obtained only on small-scale, manually-assembled classes.
aclanthology.org
Showing the best result for this search. See all results