Statistical versus symbolic parsing for captioned-information retrieval [article]

Neil C. Rowe (Code CS/Rp, Department of Computer Science, Naval Postgraduate School, Monterey)
1994 arXiv   pre-print
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.
arXiv:cmp-lg/9408008v1 fatcat:3pj2g4tpp5grnch2yutbiteg4i