Our model outperforms the log-linear translation models with/without embedding features on Chinese-to-English and J apanese-to-English translation tasks .

On both Chinese-to-English and J apanese-to-English translation tasks , experiment results show that our model can leverage the shortcomings suffered by the log-linear model, and thus achieves significant improvements over the log-linear based translation.

We conduct our experiments on the Chinese-to-English and J apanese-to-English translation tasks .

Although there are serious overlaps between h and h’ for AdNN-Hiero-D which may limit its generalization abilities, as shown in Table 3, it is still comparable to L—Hiero on the J apanese-to-English task, and significantly outperforms L-Hiero on the Chinese-to-English translation task .

Our experiments on Urdu-English, Arabic-English, and Farsi-English translation tasks all demonstrate improvements over competitive baseline systems.

The corpora statistics of these translation tasks are summarised in Table 2.

The time complexity of our inference algorithm is 0(n6), which can be prohibitive for large scale machine translation tasks .

Table 3 shows the BLEU scores for the three translation tasks UR/AlUFA—>EN based on our method against the baselines.

Moreover our approach results in consistent translation improvements across a number of translation tasks compared to Neubig et al.’s method, and a competitive phrase-based baseline.

We perform a large-scale empirical evaluation of our obtained system, which demonstrates that we significantly beat a realistic tree-to-tree baseline on the WMT 2009 English —> German translation task .

We demonstrated that our EMBOT-based machine translation system beats a standard tree-to-tree system (Moses tree-to-tree) on the WMT 2009 translation task English —> German.

The compared systems are evaluated on the English-to-German13 news translation task of WMT 2009 (Callison-Burch et al., 2009).

We evaluate our new system on the WMT 2009 shared translation task English —> German.

We integrate our proposed model into a state-of-the-art string-to-dependency translation system and demonstrate the efficacy of our proposal in a large-scale Chinese-to-English translation task .

In a large scale Chinese-to-English translation task , we achieve a significant improvement over a strong baseline.

We show the efficacy of our proposal in a large-scale Chinese-to-English translation task where the introduction of our TNO model provides a significant gain over a state-of-the-art string-to-dependency SMT system (Shen et al., 2008) that we enhance with additional state-of-the-art features.

Here, we would like to point out that even in this simple example where all local decisions are made accurate, this ambiguity occurs and it would occur even more so in the real translation task where local decisions may be highly inaccurate.

(Wang et al., 2007) present a pre-reordering method for Chinese-English translation task .

The CRFs achieves lower error rate on the tagging task but RNN trained model is better for the translation task .

However, the tree-based jump model relies on manually designed reordering rules which does not exist for many language pairs while our model can be easily adapted to other translation tasks .

Unlike some text-to-text translation tasks, text simplification is a monolingual translation task allowing for text in both the input and output domain to be used for training the language model.

text compression, text simplification and summarization) can be viewed as monolingual translation tasks , translating between text variations within a single language.

This is not the case for all monolingual translation tasks (Knight and Marcu, 2002; Cohn and Lapata, 2009).