We integrate our method into a state-of-the-art baseline translation system and show that it consistently improves the performance of the baseline system on various NIST MT test sets.

For example, if the baseline system knows that the translation for “EWE )E‘L’EX” is “Hong Kong Governor”, and it also knows that “7% E” is an abbreviation of “éfi , then it can translate “7%?” to “Hong Kong Governor”.

We also need to make sure that the baseline system has at least one valid translation for the full-form phrase.

Moreover, our approach integrates the abbreviation translation component into the baseline system in a natural way, and thus is able to make use of the minimum-error-rate training (Och, 2003) to automatically adjust the model parameters to reflect the change of the integrated system over the baseline system .

o Step-5: augment the baseline system with translation entries obtained in Step-4.

Moreover, obtaining a list using a dedicated tagger does not guarantee that the baseline system knows how to translate the list.

On the contrary, in our approach, since the Chinese entities are translation outputs for the English entities, it is ensured that the baseline system has translations for these Chinese entities.

The language model is applied by means of an N -best rescoring step, which allows to directly measure the performance gains relative to the baseline system without rescoring.

We report a significant reduction in word error rate compared to a state-of-the-art baseline system .

For a given test set we could then compare the word error rate of the baseline system with that of the extended system employing the grammar-based language model.

Our primary aim was to design a task which allows us to investigate the properties of our grammar-based approach and to compare its performance with that of a competitive baseline system .

As shown in Table l, the grammar-based language model reduced the word error rate by 9.2% relative over the baseline system .

Besides proposing an improved language model, this paper presents experimental results for a much more difficult and realistic task and compares them to the performance of a state-of-the-art baseline system .

Propagating the uncertainty of the baseline system by using more input hypotheses consistently improves performance across the different methods, with an additional improvement of between .2 and .4 BLEU points.

In all scenarios, two human judges (native speakers of these languages) evaluated 100 sentences that had different translations by the baseline system and our model.

The judges were given the reference translations but not the source sentences, and were asked to classify each sentence pair into three categories: (1) the baseline system is better (score=-1), (2) the output of our model is better (score=l), or (3) they are of the same quality (score=0).

We propose a heuristic for tuning posterior decoding in the absence of annotated alignment data and show improvements over baseline systems for six different

The baseline system uses GIZA model 4 alignments and the open source Moses phrase-based machine translation toolkit2, and performed close to the best at the competition last year.

We report BLEU scores using a script available with the baseline system .

It is observed that significant enhancement of accuracy over the baseline system which use word features is obtained.

But in the baseline system addition of word features (wi_2 and 212,42) over the same feature decrease the f-value from 75.6 to 72.65.

The best accuracy (75.6 f-value) of the baseline system is obtained using the binary NomPSP feature along with word feature (wi_1, wi+1), suffix and digit information.

For these arguments, we simply filled in using our baseline system (specifically, any non-core argument which did not overlap an argument predicted by our model was added to the labeling).

achieving a statistically significant increase over the Baseline system (according to confidence intervals calculated for the Conll-2005 results).

The Transforms model correctly labels the arguments of “buy”, while the Baseline system misses the ARGO.

Experimental results on the NIST MT-2005 Chinese-English translation task show that our method statistically significantly outperforms the baseline systems .

We set three baseline systems : Moses (Koehn et al., 2007), and SCFG-based and STSG-based tree-to-tree translation models (Zhang et al., 2007).

In this subsection, we first report the rule distributions and compare our model with the three baseline systems .