WMT2014

This paper explores a number of simple and effective techniques to adapt statisti- cal machine translation (SMT) systems in the medical domain. Comparative exper- iments are conducted on large corpora …...

This paper describes adapting statistical machine translation (SMT) systems to medical domain using in-domain and general-domain data as well as web- crawled in-domain resources. In order to complement the limited …...

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, …...

This paper describes the IPN-UPV partici- pation on the English-to-Hindi translation task from WMT 2014 International Evalu- ation Campaign. The system presented is based on Moses and enhanced with deep …...

AbstractWe present HindEnCorp, a parallel corpus of Hindi and English, and HindMonoCorp, a monolingual corpus of Hindi in their release version 0.5. Both corpora were collected from web sources and …...

This paper describes the LAYERED met- ric which is used for the shared WMT’14 metrics task. Various metrics exist for MT evaluation: BLEU (Papineni, 2002), ME- TEOR (Alon Lavie, 2007), …...

This paper describes our Word-level QE system for WMT 2014 shared task on Spanish - English pair. Compared to WMT 2013, this year’s task is different due to the lack …...

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 …...

Human-designed sub-structures are re- quired by most of the syntax-based ma- chine translation evaluation metrics. In this paper, we propose a novel evalua- tion metric based on dependency parsing model, …...

AbstractWhile machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) …...

AbstractLong sentences have been one of the major challenges in neural machine translation (NMT). Although some approaches such as the attention mechanism have partially remedied the problem, we found that …...

AbstractResidual has been widely applied to build deep neural networks with enhanced feature propagation and improved accuracy. In the literature, multiple variants of residual structure are proposed. However, most of …...

AbstractSparse models require less memory for storage and enable a faster inference by reducing the necessary number of FLOPs. This is relevant both for time-critical and on-device computations using neural …...