Statistical versus symbolic parsing for captioned-information retrieval
Abstract
Description
We discuss implementation issues of MARIE-1, a mostly symbolic parser fully implemented, and MARIE-2, a more statistical parser partially implemented. They address a corpus of 100,000 picture captions. We argue that the mixed approach of MARIE-2 should be better for this corpus because its algorithms (not data) are simpler.
Workshop on the Balancing Act, ACL-94, Las Cruces NM, July 1994
Workshop on the Balancing Act, ACL-94, Las Cruces NM, July 1994