4 papers
Unification-Based Glossing
Vasileios Hatzivassiloglou, Kevin Knight
We present an approach to syntax-based machine translation that combines unification-style interpretation with statistical processing. This approach enables us to translate any Jap…
Two-level, Many-Paths Generation
Kevin Knight, Vasileios Hatzivassiloglou
Large-scale natural language generation requires the integration of vast amounts of knowledge: lexical, grammatical, and conceptual. A robust generator must be able to operate well…
Filling Knowledge Gaps in a Broad-Coverage Machine Translation System
Kevin Knight, Ishwar Chander, Matthew Haines +6
Knowledge-based machine translation (KBMT) techniques yield high quality in domains with detailed semantic models, limited vocabulary, and controlled input grammar. Scaling up alon…
Integrating Knowledge Bases and Statistics in MT
Kevin Knight, Ishwar Chander, Matthew Haines +7
We summarize recent machine translation (MT) research at the Information Sciences Institute of USC, and we describe its application to the development of a Japanese-English newspap…