Statistical versus symbolic parsing for captioned-information retrieval
classification
cmp-lg
cs.CL
keywords
corpusimplementedmarie-2parserstatisticalsymbolicaddressalgorithms
read the original abstract
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.
This paper has not been read by Pith yet.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.