We present APRO, a new method for machine translation tuning that can handle large feature sets. As opposed to other popular methods (e.g., MERT, MIRA, PRO), which involve randomness and require multiple runs to obtain a reliable result, APRO gives …
It is common knowledge that translation is an ambiguous, 1-to-n mapping process, but to date, our community has produced no empirical estimates of this ambiguity. We have developed an annotation tool that enables us to create representations that …
Given several systems' automatic translations of the same sentence, we show how to combine them into a confusion network, whose various paths represent composite translations that could be considered in a subsequent rescoring step. We build our …
This paper describes a new method to compare reordering constraints for Statistical Machine Translation. We investigate the best possible (oracle) BLEU score achievable under different reordering constraints. Using dynamic programming, we efficiently …
Designers of SMT system have begun to experiment with tree-structured translation models. Unfortunately, SMT systems driven by such models are even more difficult to build than the already complicated WFST-based systems. The purpose of our workshop …