posted on 2009-09-01, 00:00authored byTeruko Mitamura, Eric Nyberg, Jaime G. Carbonell
Knowledge-based interlingual machine translation
systems produce semantically accurate translations,
but typically require massive knowledge acquisition.
This paper describes KANT, a system that
reduces this requirement to produce practical, scalable,
and accurate KBMT applications. First, the
set of requirements is discussed, then the full KANT
architecture is illustrated, and finally results from a
fully implemented prototype are presented.