Filling Knowledge Gaps in a Broad-Coverage Machine Translation System

Simple item page
dc.creatorKnight, Kevin
dc.creatorChander, Ishwar
dc.creatorHaines, Matthew
dc.creatorHatzivassiloglou, Vasileios
dc.creatorHovy, Eduard
dc.creatorIida, Masayo
dc.creatorLuk, Steve K.
dc.creatorWhitney, Richard
dc.creatorYamada, Kenji
dc.date1995-06-10
dc.date.accessioned2026-07-07T09:09:54Z
dc.date.available2026-07-07T09:09:54Z
dc.descriptionKnowledge-based machine translation (KBMT) techniques yield high quality in domains with detailed semantic models, limited vocabulary, and controlled input grammar. Scaling up along these dimensions means acquiring large knowledge resources. It also means behaving reasonably when definitive knowledge is not yet available. This paper describes how we can fill various KBMT knowledge gaps, often using robust statistical techniques. We describe quantitative and qualitative results from JAPANGLOSS, a broad-coverage Japanese-English MT system.
dc.description7 pages, Compressed and uuencoded postscript. To appear: IJCAI-95
dc.identifierhttps://arxiv.org/abs/cmp-lg/9506009
dc.identifierhttp://arxiv.org/abs/cmp-lg/9506009
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/151204
dc.subjectComputation and Language
dc.titleFilling Knowledge Gaps in a Broad-Coverage Machine Translation System
dc.typetext

Files

Collections

arXiv