We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
of somewhat abstracting away from the literal physiological measurements of articulation that are so closely tied to the acoustic signal, and with some additional computational bur...
We present a method for improving word alignment for statistical syntax-based machine translation that employs a syntactically informed alignment model closer to the translation m...
Producing machine translation (MT) for the many minority languages in the world is a serious challenge. Minority languages typically have few resources for building MT systems. Fo...
Statistical Machine Translation (SMT) is based on alignment models which learn from bilingual corpora the word correspondences between source and target language. These models are...