Automatic word alignment is a key step in training statistical machine translation systems. Despite much recent work on word alignment methods, alignment accuracy increases often ...
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...
Tree Adjoining Grammars have well-known advantages, but are typically considered too difficult for practical systems. We demonstrate that, when done right, adjoining improves tran...
We employ statistical methods to analyze, generate, and translate rhythmic poetry. We first apply unsupervised learning to reveal word-stress patterns in a corpus of raw poetry. W...
Parallel corpora are critical resources for machine translation research and development since parallel corpora contain translation equivalences of various granularities. Manual a...