Large-scale discriminative machine translation promises to further the state-of-the-art, but has failed to deliver convincing gains over current heuristic frequency count systems. We argue that a principle reason for this failure is not dealing with multiple, equivalent translations. We present a translation model which models derivations as a latent variable, in both training and decoding, and is fully discriminative and globally optimised. Results show that accounting for multiple derivations does indeed improve performance. Additionally, we show that regularisation is essential for maximum conditional likelihood models in order to avoid degenerate solutions. 1

We present a new phrase-based conditional exponential family translation model for statistical machine translation. The model operates on a feature representation in which sentence level translations are represented by enumerating all the known phrase level translations that occur inside them. This makes the model a good match with the commonly used phrase extraction heuristics. The model’s predictions are properly normalized probabilities. In addition, the model automatically takes into account information provided by phrase overlaps, and does not suffer from reference translation reachability problems. We have implemented an open source translation system Sinuhe based on the proposed translation model. Our experiments on Europarl and GigaFrEn corpora demonstrate that finding the unique MAP parameters for the model on large scale data is feasible with simple stochastic gradient methods. Sinuhe is fast and memory efficient, and the BLEU scores obtained by it are only slightly inferior to those of Moses. 1

This paper extends previous work on extracting parallel sentence pairs from comparable data (Munteanu and Marcu, 2005). For a given source sentence S, a maximum entropy (ME) classifier is applied to a large set of candidate target translations. A beam-search algorithm is used to abandon target sentences as non-parallel early on during classification if they fall outside the beam. This way, our novel algorithm avoids any document-level prefiltering step. The algorithm increases the number of extracted parallel sentence pairs significantly, which leads to a BLEU improvement of about 1 % on our Spanish-English data. 1