On two Chinese-English tasks, our semi-supervised DAE features obtain statistically significant improvements of l.34/2.45 (IWSLT) and 0.82/1.52 (NIST) BLEU points over the unsupervised DBN features and the baseline features, respectively.

The results also demonstrate that DNN (DAE and HCDAE) features are complementary to the original features for SMT, and adding them together obtain statistically significant improvements of 3.16 (IWSLT) and 2.06 (NIST) BLEU points over the baseline features.

Adding new DNN features as extra features significantly improves translation accuracy (row 2-17 vs. 1), with the highest increase of 2.45 (IWSLT) and 1.52 (NIST) (row 14 vs. 1) BLEU points over the baseline features.

Also, adding more input features (X vs. X1) not only significantly improves the performance of DAE feature learning, but also slightly improves the performance of DBN feature learning.

To address the first shortcoming, we adapt and extend some simple but effective phrase features as the input features for new DNN feature leam-ing, and these features have been shown significant improvement for SMT, such as, phrase pair similarity (Zhao et al., 2004), phrase frequency, phrase length (Hopkins and May, 2011), and phrase generative probability (Foster et al., 2010), which also show further improvement for new phrase feature learning in our experiments.

Our semi-supervised DAE features significantly outperform the unsupervised DBN features and the baseline features, and our introduced input phrase features significantly improve the performance of DAE feature

To improve word ordering decisions, White & Rajkumar (2012) demonstrated that incorporating a feature into the ranker inspired by Gibson’s (2000) dependency locality theory can deliver statistically significant improvements in automatic evaluation scores, better match the distributional characteristics of sentence orderings, and significantly reduce the number of serious ordering errors (some involving vicious ambiguities) as confirmed by a targeted human evaluation.

With the SVM reranker, we obtain a significant improvement in BLEU scores over

tures and the n-best parse features contributed to achieving a significant improvement compared to the perceptron model.

The complete model, BBS+dep+nbest, achieved a BLEU score of 88.73, significantly improving upon the perceptron model (p < 0.02).

However, as shown in Table 2, none of the parsers yielded significant improvements on the top of the perceptron model.

We investigate this technique in the context of English-to-Arabic and English-to-Finnish translation, showing significant improvements in translation quality over desegmentation of l-best decoder outputs.

We have also applied our approach to English-to-Finnish translation, and although segmentation in general does not currently help, we are able to show significant improvements over a 1-best desegmentation baseline.

We demonstrate that significant improvements in translation quality can be achieved by training a linear model to re-rank this transformed translation space.

In fact, even with our lattice desegmenter providing a boost, we are unable to see a significant improvement over the unsegmented model.

Nonetheless, the 1000-best and lattice desegmenters both produce significant improvements over the 1-best desegmentation baseline, with Lattice Deseg achieving a 1-point improvement in TER.

Experimental results show that our method significantly improves translation accuracy in the NIST Chinese-to-English translation task compared to a state-of-the-art baseline.

It is a significant improvement over the state-of-the-art Hiero system, as well as a conventional LDA-based method.

Experimental results demonstrate that our model significantly improves translation

They incorporated the bilingual topic information into language model adaptation and lexicon translation model adaptation, achieving significant improvements in the large-scale evaluation.

Experiments on Chinese-English translation show that the reordering approach can significantly improve a state-of-the-art hierarchical phrase-based translation system.

Experiments on Chinese-English translation show that the reordering approach can significantly improve a state-of-the-art hierarchical phrase-based translation system.

We clearly see that using gold syntactic reordering types significantly improves the performance (e.g., 34.9 vs. 33.4 on average) and there is still some room for improvement by building a better maximum entropy classifiers (e.g., 34.9 vs. 34.3).

Using unlabeled data with the results of Berkeley Parser (“Unlabeled <— B”) significantly improves parsing accuracy by 0.55% (93.40-92.85) on English and 1.06% (83.34-82.28) on Chinese.

However, we find that although the parser significantly outperforms the supervised GParser on English, it does not gain significant improvement over co-training with ZPar (“Unlabeled <— Z”) on both English and Chinese.

All above work leads to significant improvement on parsing accuracy.

A statistically significant improvement of 4.1% is obtained with the use of all three features over SWING.

to guide the use of timelines such that significant improvements in R-2 over SWING are obtained.

Compared to a competitive baseline, significant improvements of up to 4.1% are obtained.

Through experiments, we demonstrate that by introducing character-level POS information, the performance of a baseline morphological analyzer can be significantly improved .

The results show that, while the differences between the baseline model and the proposed model in word segmentation accuracies are small, the proposed model achieves significant improvement in the experiment of joint segmentati-

Through experiments, we demonstrate that by introducing character-level POS information, the performance of a baseline morphological analyzer can be significantly improved .

The experimental results show that significant improvements are achieved on various test data meanwhile the translations are more cohesive and smooth.

The experimental results show that significant improvements have been achieved on various test data, meanwhile the translations are more cohesive and smooth, which together demonstrate the effectiveness of our proposed models.

To the best of our knowledge, our work is the first attempt to exploit the source functional relationship to generate the target transitional expressions for grammatical cohesion, and we have successfully incorporated the proposed models into an SMT system with significant improvement of BLEU metrics.

Training significantly improves role labelling in the case of object-extractions, which improves the overall accuracy of the model.

This slight, though significant in Eve, deficit is counterbalanced by a very substantial and significant improvement in object-extraction labelling accuracy.

Similarly, training confers a large and significant improvement for role assignment in wh-relative constructions, but it yields less of an improvement for that-relative constructions.