We give a formal definition of one such linear-time syntactic language model, detail its relation to phrase-based decoding, and integrate the model with the Moses phrase-based translation system .

Bottom-up and top-down parsers typically require a completed string as input; this requirement makes it difficult to incorporate these parsers into phrase-based translation, which generates hypothesized translations incrementally, from left-to-right.1 As a workaround, parsers can rerank the translated output of translation systems (Och et al., 2004).

(2003) use syntactic language models to rescore the output of a tree-based translation system .

Post and Gildea (2009) use tree substitution grammar parsing for language modeling, but do not use this language model in a translation system .

The use of very large n-gram language models is typically a key ingredient in the best-performing machine translation systems (Brants et al., 2007).

This paper extends the training and tuning regime for phrase-based statistical machine translation to obtain fluent translations into morphologically complex languages (we build an English to Finnish translation system ).

In order to help with replication of the results in this paper, we have run the various morphological analysis steps and created the necessary training, tuning and test data files needed in order to train, tune and test any phrase-based machine translation system with our data.

In all the experiments conducted in this paper, we used the Moses5 phrase-based translation system (Koehn et al., 2007), 2008 version.

For evaluation against segmented translation systems in segmented forms before word reconstruction, we also segmented the baseline system’s word-based output.

Statistical machine translation systems combine the predictions of two directional models, typically using heuristic combination procedures like grow-diag-final.

Extraction-based evaluations of alignment better coincide with the role of word aligners in machine translation systems (Ayan and Dorr, 2006).

Finally, we evaluated our bidirectional model in a large-scale end-to-end phrase-based machine translation system from Chinese to English, based on the alignment template approach (Och and Ney, 2004).

Machine translation systems typically combine the predictions of two directional models, one which aligns f to e and the other e to f (Och et al., 1999).

We compare against a state-of-the-art hierarchical translation (Chiang, 2005) baseline, based on the Joshua translation system under the default training and decoding settings (j o sh—ba se).

The decoder does not employ any ‘glue grammar’ as is usual with hierarchical translation systems to limit reordering up to a certain cutoff length.

Interestingly, early on (Koehn et al., 2003) exemplified the difficulties of integrating linguistic information in translation systems .

We show that a translation system based on such a joint model can perform competitively in comparison with conditional probability models, when it is augmented with a rich latent hierarchical structure trained adequately to avoid overfitting.