We presented a translation system making use of a subcategorization database together with source-side features.

We use the hierarchical translation system that comes with the Moses SMT-package and GIZA++ to compute the word alignment, using the “grow-diag-final-and” heuristics.

We report results of two types of systems (table 5): first, a regular translation system built on surface forms (i.e., normal text) and second, four inflection prediction systems.

We first replace inflected forms by their stems or lemmas: building a translation system on a stemmed representation of the target side leads to a simpler translation task, and the morphological information contained in the source and target language parts of the translation model is more balanced.

Previous work has already introduced the idea of generating inflected forms as a postprocessing step for a translation system that has been stripped of (most) target-language-specific features.

(2010) built translation systems that predict inflected word forms based on a large array of morphological and syntactic features, obtained from both source and target side.

as a hierarchical machine translation system using a string-to-tree setup.

We use a hierarchical translation system .

Parallel text is the fuel that drives modern machine translation systems .

Even without extensive preprocessing, the data improves translation performance on strong baseline news translation systems in five different language pairs (§4).

As we have shown, it is possible to obtain parallel text for many language pairs in a variety of domains very cheaply and quickly, and in sufficient quantity and quality to improve statistical machine translation systems .

For several years, WMT used the following heuristic for ranking the translation systems:

Ostensibly the purpose of a translation competition is to determine the relative ability of a set of translation systems .

Let 8 be the space of all translation systems .

Every year, the Workshop on Machine Translation (WMT) conducts a competition between machine translation systems .

The WMT organizers invite research groups to submit translation systems in eight different tracks: Czech to/from English, French to/from English, German to/from English, and Spanish to/from English.

We demonstrated that our EMBOT-based machine translation system beats a standard tree-to-tree system (Moses tree-to-tree) on the WMT 2009 translation task English —> German.

Our contrastive system is the 6MBOT—based translation system presented here.

Besides phrase-based machine translation systems (Koehn et al., 2003), syntax-based systems have become widely used because of their ability to handle nonlocal reordering.

In this contribution, we report on our novel statistical machine translation system that uses an [MBOT-based translation model.

Model MAE RMSE p 0.5596 0.7053 MA 0.5184 0.6367 us 0.5888 0.7588 MT 0.6300 0.8270 Pooled SVM 0.5823 0.7472 Independent A SVM 0.5058 0.6351 EasyAdapt SVM 0.7027 0.8816 SINGLE-TASK LEARNING Independent A 0.5091 0.6362 Independents 0.5980 0.7729 Pooled 0.5834 0.7494 Pooled & {N} 0.4932 0.6275 MULTITASK LEARNING: Annotator Combined A 0.4815 0.6174 CombinedA & {N} 0.4909 0.6268 Combined+A 0.4855 0.6203 Combined+A & {N} 0.4833 0.6102 MULTITASK LEARNING: Translation system Combineds 0.5825 0.7482 MULTITASK LEARNING: Sentence pair CombinedT 0.5813 0.7410 MULTITASK LEARNING: Combinations Combined A, 5 0.4988 0.6490 Combined A, s & {N A, 5} 0.4707 0.6003 Combined+A, 5 0.4772 0.6094 Combined 14,51 0.4588 0.5852 Combined A, s,T & {N A, 5} 0.4723 0.6023

Models of individual annotators could be used to train machine translation systems to optimise an annotator-specific quality measure, or in active learning for corpus annotation, where the model can suggest the most appropriate instances for each annotator or the best annotator for a given instance.

Let B (i) be a square covariance matrix for the ith task descriptor of M, with a column and row for each value (e. g., annotator identity, translation system , etc.).

We address this problem using multitask learning in which we learn individual models for each context (the task, incorporating the annotator and other metadata: translation system and the source sentence) while also modelling correlations between tasks such that related tasks can mutually inform one another.

Therefore, based on this advantage, although the number of matching PASs decreases, IC-PASTR still improves the translation system using PASTR significantly.

For inside context integration, since the format of IC-PASTR is the same to PASTR4, we can use the IC-PASTR to substitute PASTR for building a PAS-based translation system directly.

In addition, since our method of rule extraction is different from (Zhai et al., 2012), we also use PASTR to construct a translation system as the baseline system, which we call “PASTR”.

Experiments show that the two PAS disambiguation methods significantly improve the baseline translation system .

Modern phrase-based machine translation systems make extensive use of word-based translation models for inducing alignments from parallel corpora.

10Using the factorised alignments directly in a translation system resulted in a slight loss in BLEU versus using the un-factorised alignments.

Leading translation systems (Chiang, 2007; Koehn et al., 2007; Marcu et al., 2006) all use some kind of multi-word translation unit, which allows translations to be produced from large canned units of text from the training corpus.

Most modern machine translation systems use phrase pairs as translation units, allowing for accurate modelling of phrase-internal translation and reordering.

We consider a process in which the target string is generated using a left-to-right order, similar to the decoding strategy used by phrase-based machine translation systems (Koehn et al., 2003).

(2011) develop a bilingual language model which incorporates words in the source and target languages to predict the next unit, which they use as a feature in a translation system .

Then we apply a state-of-the-art name translation system (Ji et al., 2009) to translate names into the target language.

The name translation system is composed of the following steps: (1) Dictionary matching based on 150,041 name translation pairs; (2) Statistical name transliteration based on a structured perceptron model and a character based MT model (Dayne and Shahram, 2007); (3) Context information extraction based re-ranking.

For those names with fewer than five instances in the training data, we use the name translation system to provide translations; for the rest of the names, we leave them to the baseline MT model to handle.

well handled by all machine translation systems 2.

2We tested other translation systems , but Google Translate gave the best results.

One of the questions posed was whether the quality of present machine translation systems would enable to learn the classification properly.

We have produced initial results in terms of rule extraction, and we will be integrating these rules into the full Italian-LIS translation system to produce improved translation of connec-t1ves.

The resulting lack of a shared written form does nothing to improve the availability of sign language corpora; bilingual corpora, which are of particular importance to a translation system , are especially rare.

Tree alignment in a variety of forms has been extensively used in machine translation systems (Gildea, 2003; Eisner, 2003; May and Knight, 2007).

They use separate translation systems for each domain, and a supervised setting, whereas we aim for a system that integrates support for multiple domains, with or without supervision.

ment a multi-domain translation system .

The translation model framework could also serve as the basis of real-time adaptation of translation systems , e. g. by using incremental means to update the weight vector, or having an incrementally trainable component model that learns from the post-edits by the user, and is assigned a suitable weight.

Preordering of a source language sentence to match target word order has proved to be useful for improving machine translation systems .

The parallel corpus is used for building our phrased based machine translation system and to add training data for our reordering model.

Dealing with word order differences between source and target languages presents a significant challenge for machine translation systems .

Typical statistical machine translation systems are batch trained with a given training data and their performances are largely influenced by the amount of data.

Most of them have been proposed in order to make translation systems perform better for resource-scarce domains when most training data comes from resource-rich domains, and ignore performance on a more generic domain without domain bias (Wang et al., 2012).

Bilingual phrases are cornerstones for phrase-based SMT systems (Och and Ney, 2004; Koehn et al., 2003; Chiang, 2005) and existing translation systems often get ‘crowd-sourced’ improvements (Levenberg et al., 2010).