Towards Hybrid Quality-Oriented Machine Translation

We present a hybrid MT architecture, combin- ing state-of-the-art linguistic processing with advanced stochastic techniques. Grounded in a theoretical reflection on the division of labor between rule-based and probabilistic elements in the MT task, we summarize per-component approaches to ranking, including empirical re- sults when evaluated in isolation. Combining component-internal scores and a number of ad- ditional sources of (probabilistic) information, we explore discriminative re-ranking of n-best lists of candidate translations through an eclectic combination of knowledge sources, and provide evaluation results for various configurations. 1 Background—Motivation