Building a Linguistic Resource (LR) is a task requiring a huge quantitative of means, human resources and funds. Though finalization of the development phase and assessment of the...
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...
This article introduces a bidirectional grammar generation system called feature structure-directed generation, developed for a dialogue translation system. The system utilizes ty...
Minimum-error-rate training (MERT) is a bottleneck for current development in statistical machine translation because it is limited in the number of weights it can reliably optimi...
Large-scale knowledge-based machine translation requires significant amounts of lexical knowledge in order to map syntactic structures to conceptual structures. This paper present...