A model of competence for corpus-based machine translation
Michaël Carl · 2000
In this paper I elaborate a model of competence for corpus-based machine translation (CBMT) along the lines of the representations used in the translation system. Representations in CBMT-systems can be rich or austere, molecular or holistic and they can be fine-grained or coarse-grained. The paper shows that different CBMT architectures are required dependent on whether a better translation quality or a broader coverage is preferred according to Boitet (1999)'s formula: "Coverage * Quality = K".