Recurrent Continuous Translation Models
Citations Over TimeTop 1% of 2013 papers
Abstract
We introduce a class of probabilistic continuous translation models called Recurrent Continuous Translation Models that are purely based on continuous representations for words, phrases and sentences and do not rely on alignments or phrasal translation units.The models have a generation and a conditioning aspect.The generation of the translation is modelled with a target Recurrent Language Model, whereas the conditioning on the source sentence is modelled with a Convolutional Sentence Model.Through various experiments, we show first that our models obtain a perplexity with respect to gold translations that is > 43% lower than that of stateof-the-art alignment-based translation models.Secondly, we show that they are remarkably sensitive to the word order, syntax, and meaning of the source sentence despite lacking alignments.Finally we show that they match a state-of-the-art system when rescoring n-best lists of translations.
Related Papers
- Pre-Translation for Neural Machine Translation.(2016)
- → Using Alignment Templates to Infer Shallow-Transfer Machine Translation Rules(2006)11 cited
- → A MULTI-ENGINE TRANSLATION APPROACH TO MACHINE TRANSLATION(2002)3 cited
- → Automatic Post-Editing Method Using Translation Knowledge Based on Intuitive Common Parts Continuum for Statistical Machine Translation(2014)
- Основные факторы улучшения машинного перевода(2015)