Statistical versus symbolic parsing for captioned-information retrieval

Simple item page
dc.creatorRowe, Neil C.
dc.date1994-08-15
dc.date.accessioned2026-07-07T09:09:27Z
dc.date.available2026-07-07T09:09:27Z
dc.descriptionWe 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.
dc.descriptionWorkshop on the Balancing Act, ACL-94, Las Cruces NM, July 1994
dc.identifierhttps://arxiv.org/abs/cmp-lg/9408008
dc.identifierhttp://arxiv.org/abs/cmp-lg/9408008
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151047
dc.subjectComputation and Language
dc.titleStatistical versus symbolic parsing for captioned-information retrieval
dc.typetext

Files

Collections

arXiv