One problem with phrase-based statistical machine translation is the problem of longdistance reordering when translating between languages with different word orders, such as Japanese-English. In this paper, we propose a method of imposing reordering constraints using document-level context. As the documentlevel context, we use noun phrases which significantly occur in context documents contain...

In this paper we improve Urdu→Hindi English machine translation through triangulation and transliteration. First we built an Urdu→Hindi SMT system by inducing triangulated and transliterated phrase-tables from Urdu–English and Hindi–English phrase translation models. We then use it to translate the Urdu part of the Urdu-English parallel data into Hindi, thus creating an artificial Hindi-English...

This paper gives the system description of the neural probabilistic language modeling (NPLM) team of Dublin City University for our participation in the system combination task in the Second Workshop on Applying Machine Learning Techniques to Optimise the Division of Labour in Hybrid MT (ML4HMT-12). We used the information obtained by NPLM as meta information to the system combination module. F...

The state-of-the-art system combination method for machine translation (MT) is the word-based combination using confusion networks. One of the crucial steps in confusion network decoding is the alignment of different hypotheses to each other when building a network. In this paper, we present new methods to improve alignment of hypotheses using word synonyms and a two-pass alignment strategy. We...

In this paper we describe the system that we develop as part of our participation in WAT 2016. We develop a system based on hierarchical phrase-based SMT for English to Hindi language pair. We perform reordering and augment bilingual dictionary to improve the performance. As a baseline we use a phrase-based SMT model. The MT models are fine-tuned on the development set, and the best configurati...

We speed up Neural Machine Translation (NMT) decoding by shrinking run-time target vocabulary. We experiment with two shrinking approaches: Locality Sensitive Hashing (LSH) and word alignments. Using the latter method, we get a 2x overall speed-up over a highly-optimized GPU implementation, without hurting BLEU. On certain low-resource language pairs, the same methods improve BLEU by 0.5 points...

In this paper we show how to automatically induce non-linear features for machine translation. The new features are selected to approximately maximize a BLEU-related objective and decompose on the level of local phrases, which guarantees that the asymptotic complexity of machine translation decoding does not increase. We achieve this by applying gradient boosting machines (Friedman, 2000) to le...

The transformer model is one of the most recently developed models for translating texts into another language. uses principle attention mechanism, surpassing previous models, such as sequence-to-sequence, in terms performance. It performed well with highly resourced English, French, and German languages. Using architecture, we investigate training modified version a low-resourced language Kurd...

MT systems are traditionally evaluated with different criteria, such as adequacy and fluency. Automatic evaluation scores are designed to match these quality parameters. In this paper we introduce a novel parameter – usability (or utility) of output, which was found to integrate both fluency and adequacy. We confronted two automated metrics, BLEU and LTV, with new data for which human evaluatio...

RWTH participated in the System Combination task of the Fourth Workshop on Statistical Machine Translation (WMT 2009). Hypotheses from 9 German→English MT systems were combined into a consensus translation. This consensus translation scored 2.1% better in BLEU and 2.3% better in TER (abs.) than the best single system. In addition, cross-lingual output from 10 French, German, and Spanish→English...