Abstract | A manual evaluation of an English-to-German translation task shows that the subcategorization information has a positive impact on translation quality through better prediction of case. |
Conclusion | We showed in a manual evaluation that the proposed features have a positive impact on translation quality . |
Experiments and evaluation | We also present a manual evaluation of our best system which shows that the new features improve translation quality . |
Experiments and evaluation | While the inflection prediction systems (1-4) are significantly12 better than the surface-form system (0), the different versions of the inflection systems are not distinguishable in terms of BLEU; however, our manual evaluation shows that the new features have a positive impact on translation quality . |
Introduction | Integrating semantic role information into SMT has been demonstrated by various researchers to improve translation quality (cf. |
Translation pipeline | This outcome, in particular that adding the lemma of the preposition to the PP node helps to improve translation quality , has been observed before in tree restructuring work for improving translation (Huang and Knight, 2006). |
Translation pipeline | 3 Preliminary experiments showed that larger windows do not improve translation quality . |
Abstract | Recent discriminative algorithms that accommodate sparse features have produced smaller than expected translation quality gains in large systems. |
Abstract | Large-scale experiments on Arabic-English and Chinese-English show that our method produces significant translation quality gains by exploiting sparse features. |
Experiments | Tables 2 and 3 show that adding tuning examples improves translation quality . |
Experiments | (2012) showed significant translation quality gains by tuning on the bitext. |
Experiments | When tuned on bitext5k the translation quality gains are significant for bitextSk-test relative to tuning on MT05/ 6/ 8, which has multiple references. |
Introduction | We conduct large-scale translation quality experiments on Arabic-English and Chinese-English. |
Experiments | We measured the overall translation quality with the help of 4-gram BLEU (Papineni et al., 2002), which was computed on tokenized and lower-cased data for both systems. |
Introduction | (2006) use syntactic annotations on the source language side and show significant improvements in translation quality . |
Introduction | (2009), and Chiang (2010), the integration of syntactic information on both sides tends to decrease translation quality because the systems become too restrictive. |
Introduction | The translation quality is automatically measured using BLEU scores, and we confirm the findings by providing linguistic evidence (see Section 5). |
Abstract | Our experiments on two machine translation quality estimation datasets show uniform significant accuracy gains from multitask learning, and consistently outperform strong baselines. |
Conclusion | Our experiments showed how our approach outperformed competitive baselines on two machine translation quality regression problems, including the highly challenging problem of predicting post-editing time. |
Introduction | In addition to annotators’ own perceptions and expectations with respect to translation quality , a number of factors can affect their judgements on specific sentences. |
Introduction | We show in our experiments on two translation quality datasets that these multitask learning strategies are far superior to training individual per-task models or a single pooled model, and moreover that our multitask learning approach can achieve similar performance to these baselines using only a fraction of the training data. |
Abstract | Additionally, we also propose a new MT metric to appropriately evaluate the translation quality of informative words, by assigning different weights to different words according to their importance values in a document. |
Experiments | Furthermore, using external name translation table only did not improve translation quality in most test sets except for BOLT2. |
Experiments | Although the proposed model has significantly enhanced translation quality , some challenges remain. |
Name-aware MT Evaluation | In order to properly evaluate the translation quality of NAMT methods, we propose to modify the BLEU metric so that they can dynamically assign more weights to names during evaluation. |
Abstract | Experiments show that our approach helps to achieve significant improvements on translation quality . |
Experiment | The translation quality is evaluated by case-insensitive BLEU-4 with shortest length penalty. |
PAS-based Translation Framework | This harms the translation quality . |
Related Work | By incorporating the rich context information as features, they chose better rules for translation and yielded stable improvements on translation quality . |
Abstract | We apply our method for the domain adaptation task and the extensive experiments show that our proposed method can substantially improve the translation quality . |
Experiments | Our purpose is to induce phrase pairs to improve translation quality for domain adaptation. |
Experiments | some good methods to explore the potential of the given data to improve the translation quality . |