Experiments on several language pairs demonstrate that the proposed model matches the accuracy of traditional two-step word alignment/phrase extraction approach while reducing the phrase table to a fraction of the original size.

Machine translation systems using phrase tables learned directly by the proposed model were able to achieve accuracy competitive with the traditional pipeline of word alignment and heuristic phrase extraction, the first such result for an unsupervised model.

In addition, we will test probabilities learned using the proposed model with an ITG—based decoder.

We will also examine the applicability of the proposed model in the context of hierarchical phrases (Chiang, 2007), or in alignment using syntactic structure (Galley et al., 2006).

For the proposed models , we train for 100 iterations, and use the final sample acquired at the end of the training process for our experiments using a single sample6.

All of these techniques are applicable to the proposed model , but we choose to apply the sentence-based blocked sampling of Blunsom and Cohn (2010), which has desirable convergence properties compared to sampling single alignments.

In the proposed model , at each branch in the tree, we first attempt to generate a phrase pair from the phrase pair distribution, falling back to ITG-based divide and conquer strategy to generate phrase pairs that do not exist (or are given low probability) in the phrase distribution.

However, as the proposed models tend to align relatively large phrases, we also use two other techniques to create smaller alignment chunks that prevent sparsity.

We plan to examine variational inference for the proposed models in future work.