2016

Domain Control for Neural Machine Translation

Kobus, Catherine, Crego, Josep, Senellart, Jean

Understand

Machine translation systems are very sensitive to the domains they were trained on.

  • Several domain adaptation techniques have been deeply studied.
  • We propose a new technique for neural machine translation (NMT) that we call domain control which is performed at runtime using a unique neural network covering multiple domains.
  • The presented approach shows quality improvements when compared to dedicated domains translating on any of the covered domains and even on out-of-domain data.

Built on

  • Adaptation of the translation model for statistical machine translation based on information retrieval

    Almut Silja Hildebrand, Matthias Eck, Stephan Vogel, and Alex Waibel. 2005 · 2005

    Earlier work this paper cites.

  • Selecting relevant text subsets from web-data for building topic specific language models

    Abhinav Sethy, Panayiotis Georgiou, and Shrikanth Narayanan. 2006 · 2006

    Earlier work this paper cites.

  • Mixture-model adaptation for SMT

    George Foster and Roland Kuhn. 2007 · 2007

    Earlier work this paper cites.

  • Experiments in domain adaptation for statistical machine translation

    Philipp Koehn and Josh Schroeder. 2007 · 2007

    Earlier work this paper cites.

  • Large and diverse language models for statistical machine translation

    Holger Schwenk and Philipp Koehn. 2008 · 2008

    Earlier work this paper cites.

  • Intelligent selection of language model training data

    Robert C. Moore and William Lewis. 2010 · 2010

    Earlier work this paper cites.

Similar

  • Parallel data, tools and interfaces in opus

    Jörg Tiedemann. 2012 · 2012

    Cited alongside, same era.

  • Neural machine translation by jointly learning to align and translate

    Original

    Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014 · 2014

    Cited alongside, same era.

  • Recurrent neural network regularization

    Original

    Wojciech Zaremba, Ilya Sutskever, and Oriol Vinyals. 2014 · 2014

    Cited alongside, same era.

  • Stanford neural machine translation systems for spoken language domains

    Thang Luong and Christopher D. Manning. 2015 · 2015

    Cited alongside, same era.

  • Effective approaches to attention-based neural machine translation

    Thang Luong, Hieu Pham, and Christopher D. Manning. 2015 · 2015

    Cited alongside, same era.

Then

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…