Call For Papers

The workshop will consist of a mixture of invited talks and contributed talks, with panel sessions.  To avoid the "mini-conference effect", there is no poster session.

We anticipate a total of six contributed talks of 20 minutes each, distributed evenly over the following three high-level areas:
  • Being data-driven.
    • What can and cannot be done with ​offline evaluation on fixed data sets?  How can we facilitate development of these offline evaluation tasks in the public domain?
    • What is the role of online evaluation (e.g. as a benchmark?), and how would we make it accessible to the general community?
    • What can be done with simulated environments, or tasks where machines communicate solely with each other?
  • Build complete applications.
    • ​Do we need to build a irreducible end-to-end system, or can we define modules with abstractions that do not leak?
    • ​How do we ease the burden on the human designer of specifying or bootstrapping the system?
  • Model innovation.
    • What are the requisite capabilities for learning architectures, ​and where are the deficiencies in our current architectures?
    • How can we beneficially incorporate linguistic knowledge into our architectures?​

Additional Information

  • The papers should be in NIPS (blind) submission format.
  • The paper should not exceed more than 4 pages (including references).
  • The authors of all the accepted papers will be expected to give a 20 minute talk (15 for the talk + 5 min for questions) and participate in a panel session.
  • Accepted papers will be displayed on the website.
  • There will be no posters.
  • Submissions close at the end of the day of October 23rd, Pacific Time.
    • The deadline has been extended two weeks.