Description

The 1st Workshop on Neural Machine Translation is a new annual workshop that will be co-located with ACL 2017 (Vancouver, July 30-August 4, 2017). Neural Machine Translation (NMT) is a simple new architecture for getting machines to learn to translate. Despite being relatively recent, NMT has demonstrated promising results and attracted much interest, achieving state-of-the-art results on a number of shared tasks. This workshop aims to cultivate research in neural machine translation and other aspects of machine translation and multilinguality that utilize neural models. The workshop is broad in scope and invites original research contributions on topics that include, but are not limited to the following:

  • Incorporating linguistic insights: syntax, alignment, reordering, etc.

  • Combining NMT & SMT

  • Handling resource-limited domains

  • Utilizing more data in NMT: monolingual, multilingual resources

  • Multi-task learning for NMT

  • NMT for mobile devices

  • Analysis and visualization of NMT models

  • Beyond sentence-level translation

  • Beyond maximum-likelihood estimation

  • Neural Machine Generation


We ambitiously aim to complement the main conference by trying to achieve the following goals:

  • Synthesize the current state of knowledge in NMT: During the workshop, we will hold a panel session attempting to answer major questions about NMT -- both specific (what methods do we use to optimize our systems? how do we perform search?), and general (what will be the long-lasting ideas, which problems have been essentially solved, etc.) as well as highlight potential areas of research in the future. We plan to write up and publish a survey paper at the end of the workshop to summarize experts’ knowledge and opinions on the current state of NMT.
  • Expand the research horizons in NMT: In addition, we hope to hold a brainstorming session about what kinds of novel tasks or what kind of new information we can incorporate to MT as a whole using the tools provided by NMT. Based on people’s proposals, we hope to organize relevant shared tasks in subsequent years, lowering the entry bar for new researchers into NMT in a similar way to which WMT did for SMT.

We expect the highlight of the workshop to be this panel and brainstorming sessions where participants can understand and help shape the future of this rapidly growing field. We will also feature invited talks from leading researchers (Chris Dyer, Kevin Knight, Quoc Le, Alexander Rush, Rico Sennrich) in the field, and also accept submissions of both completed and forward-looking work which will be presented either as oral presentations or during a poster session.