Abstract | 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. |
Introduction | 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”. |
Introduction | We also need to make sure that the baseline system has at least one valid translation for the full-form phrase. |
Introduction | 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 . |
Unsupervised Translation Induction for Chinese Abbreviations | o Step-5: augment the baseline system with translation entries obtained in Step-4. |
Unsupervised Translation Induction for Chinese Abbreviations | Moreover, obtaining a list using a dedicated tagger does not guarantee that the baseline system knows how to translate the list. |
Unsupervised Translation Induction for Chinese Abbreviations | 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. |
Abstract | 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. |
Abstract | We report a significant reduction in word error rate compared to a state-of-the-art baseline system . |
Experiments | 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. |
Experiments | 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 . |
Experiments | As shown in Table l, the grammar-based language model reduced the word error rate by 9.2% relative over the baseline system . |
Introduction | 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 . |
MT performance results | 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. |
MT performance results | 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. |
MT performance results | 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). |
Introduction | We propose a heuristic for tuning posterior decoding in the absence of annotated alignment data and show improvements over baseline systems for six different |
Phrase-based machine translation | 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. |
Phrase-based machine translation | We report BLEU scores using a script available with the baseline system . |
Conclusion | It is observed that significant enhancement of accuracy over the baseline system which use word features is obtained. |
Evaluation of NE Recognition | 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. |
Maximum Entropy Based Model for Hindi NER | 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. |
Experiments | 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). |
Experiments | achieving a statistically significant increase over the Baseline system (according to confidence intervals calculated for the Conll-2005 results). |
Experiments | The Transforms model correctly labels the arguments of “buy”, while the Baseline system misses the ARGO. |
Abstract | Experimental results on the NIST MT-2005 Chinese-English translation task show that our method statistically significantly outperforms the baseline systems . |
Experiments | 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). |
Experiments | In this subsection, we first report the rule distributions and compare our model with the three baseline systems . |