Hierarchical phrase-based translation with weighted finite state transducers

This dissertation is focused in the Statistical Machine Translation field (SMT), particularly in hierarchical phrase-based translation frameworks. We first study and redesign hierarchical models using several filtering techniques. Hierarchical search spaces are based on automatically extracted translation rules. As originally defined they are too big to handle directly without filtering. In this thesis we create more space-efficient models, aiming at faster decoding times without a cost in performance. We propose more refined strategies such as pattern filtering and shallow-n grammars. The aim is to reduce a priori the search space as much as possible without losing performance (or even improving it), so that search errors will be avoided. We also propose a new algorithm in the hierarchical phrase-based machine translation framework, called HiFST. For the first time, as far as we are aware, an SMT system combines successfully knowledge from two other research areas simultaneously: parsing, and weighted finite-state technology. In this way we are able to build a more efficient decoding tool, taking the advantages of both worlds: the capability of deep syntax reordering with parsing, and the compact representation and powerful semiring operations of weighted finitestate transducers. Combined with our findings for hierarchical grammars, we are able to build search-error free translation systems with state-of-the-art performance.