German-English

We propose a backoff model for phrase- based machine translation that translates unseen word forms in foreign-language text by hierarchical morphological ab- stractions at the word and the phrase level. …...

The Edinburgh submissions to the shared task of the Third Workshop on Statistical Machine Translation (WMT-2008) incorporate recent advances to the open source Moses system. We made a special effort …...

Automatically clustering words from a mono- lingual or bilingual training corpus into classes is a widely used technique in statisti- cal natural language processing. We present a very simple and …...

This paper describes LIMSI’s submis- sions to the shared WMT’13 translation task. We report results for French-English, German-English and Spanish-English in both directions. Our submissions use n-code, an open source …...

This article reports on mass experiments sup- porting the idea that data extracted from strongly comparable corpora may successfully be used to build statistical machine translation systems of reasonable translation …...

This paper describes the string-to-tree sys- tems built at the University of Edin- burgh for the WMT 2014 shared trans- lation task. We developed systems for English-German, Czech-English, French- English, …...

We describe the CMU systems submitted to the 2014 WMT shared translation task. We participated in two language pairs, German–English and Hindi–English. Our innovations include: a label coarsening scheme for …...

In this year’s WMT translation task, Finnish-English was introduced as a lan- guage pair of competition for the first time. We present experiments examining sev- eral variations on a morphologically-aware …...

AbstractBilingual sequence models improve phrase-based translation and reordering by overcoming phrasal independence assumption and handling long range reordering. However, due to data sparsity, these models often fall back to very …...

This paper presents the contribution of the Unbabel team to the WMT 2017 Shared Task on Translation Quality Estimation. We participated on the word-level and sentence-level tracks. We describe our …...

AbstractRecent machine translation shared tasks have shown top-performing systems to tie or in some cases even outperform human translation. Such conclusions about system and human performance are, however, based on …...

Translating text that diverges from the training domain is a key challenge for machine trans- lation. Domain robustness—the generalization of models to unseen test domains—is low for both statistical (SMT) …...

AbstractAdaptive policies are better than fixed policies for simultaneous translation, since they can flexibly balance the tradeoff between translation quality and latency based on the current context information. But previous …...

AbstractThis paper describes the University of Edinburgh’s submission of German <-> English systems to the WMT2020 Shared Tasks on News Translation and Zero-shot Robustness....

AbstractThis paper presents a fine-grained test suite for the language pair German–English. The test suite is based on a number of linguistically motivated categories and phenomena and the semi-automatic evaluation …...

AbstractThe PROMT systems are trained with the MarianNMT toolkit. All systems use the transformer-big configuration. We use BPE for text encoding, the vocabulary sizes vary from 24k to 32k for …...

AbstractNeural sequence generation models are known to “hallucinate”, by producing outputs that are unrelated to the source text. These hallucinations are potentially harmful, yet it remains unclear in what conditions …...