Montreal Neural Machine Translation Systems for WMT’15

Citations Over TimeTop 1% of 2015 papers

Abstract

Neural machine translation (NMT) systems have recently achieved results comparable to the state of the art on a few translation tasks, including EnglishFrench and EnglishGerman. The main purpose of the Montreal Institute for Learning Algorithms (MILA) submission to WMT'15 is to evaluate this new approach on a greater variety of language pairs. Furthermore, the human evaluation campaign may help us and the research community to better understand the behaviour of our systems. We use the RNNsearch architecture, which adds an attention mechanism to the encoderdecoder. We also leverage some of the recent developments in NMT, including the use of large vocabularies, unknown word replacement and, to a limited degree, the inclusion of monolingual language models.

Related Papers

• → Supervised Attentions for Neural Machine Translation(2016)124 cited
• MATREX: The DCU MT System for WMT 2010(2010)
• → SMT and SPE machine translation systems for WMT'09(2009)22 cited
• → English to Kurdish Rule-based Machine Translation System(2018)4 cited
• → Bi-Directional Differentiable Input Reconstruction for Low-Resource Neural Machine Translation(2018)