Abstract | In this paper, we propose to consider the translation quality of each sentence in the English-to-Chinese cross-language summarization process. |
Abstract | First, the translation quality of each English sentence in the document set is predicted with the SVM regression method, and then the quality score of each sentence is incorporated into the summarization process. |
Abstract | Finally, the English sentences with high translation quality and high informativeness are selected and translated to form the Chinese summary. |
Introduction | However, though machine translation techniques have been advanced a lot, the machine translation quality is far from satisfactory, and in many cases, the translated texts are hard to understand. |
Introduction | In order to address the above problem, we propose to consider the translation quality of the English sentences in the summarization process. |
Introduction | In particular, the translation quality of each English sentence is predicted by using the SVM regression method, and then the predicted MT quality score of each sentence is incorporated into the sentence evaluation process, and finally both informative and easy-to-translate sentences are selected and translated to form the Chinese summary. |
Related Work 2.1 Machine Translation Quality Prediction | In this study, we further predict the translation quality of an English sentence before the machine translation process, i.e., we do not leverage reference translation and the target sentence. |
The Proposed Approach | Each English sentence is associated with a score indicating its translation quality . |
The Proposed Approach | An English sentence with high translation quality score is more likely to be selected into the original English summary, and such English summary can be translated into a better Chinese summary. |
Introduction | Our results show, that this leads to a better translation quality . |
Introduction | Our results show that the proposed phrase model training improves translation quality on the test set by 0.9 BLEU points over our baseline. |
Phrase Model Training | As (DeNero et al., 2006) have reported improvements in translation quality by interpolation of phrase tables produced by the generative and the heuristic model, we adopt this method and also report results using lo g-linear interpolation of the estimated model with the original model. |
Related Work | The model shows improvements in translation quality over the single-word-based IBM Model 4 (Brown et al., 1993) on a subset of the Canadian Hansards corpus. |
Related Work | They observe that due to several constraints and pruning steps, the trained phrase table is much smaller than the heuristically extracted one, while preserving translation quality . |
Abstract | The experimental results show that our method improves the performance of both word alignment and translation quality significantly. |
Experiments on Phrase-Based SMT | Here, we investigate three different collocation models for translation quality improvement. |
Experiments on Phrase-Based SMT | When the phrase collocation probabilities are incorporated into the SMT system, the translation quality is improved, achieving an absolute improvement of 0.85 BLEU score. |
Experiments | We evaluate the translation quality using the BLEU-4 metric (Pap-ineni et al., 2002), which is calculated by the script mteval-vllb.pl with its default setting which is case-insensitive matching of n-grams. |
Experiments | Those results suggest that restrictions on 625 rules won’t hurt the performance, but restrictions on 525 will hurt the translation quality badly. |
Experiments | This suggests that using dependency language model really improves the translation quality by less than 1 BLEU point. |