Let's Discuss: Learning Methods for Dialogue
NIPS 2016 Workshop
10 December 2016
Humans conversing naturally with machines is a staple of science fiction.
Building agents capable of mutually coordinating their states and actions via
communication, in conjunction with human agents, would be one of the greatest
engineering feats of human history. In addition to the tremendous economic
potential of this technology, the ability to converse appears intimately
related to the overall goal of AI.
Although dialogue has been an active area within the linguistics and NLP
communities for decades, the wave of optimism in the machine learning community
has inspired increased interest from researchers, companies, and foundations.
The NLP community has enthusiastically embraced and innovated neural
information processing systems, resulting in substantial relevant activity
published outside of NIPS. The goal of this forum is increased interaction
(dialogue!) between these communities at NIPS to accelerate creativity and
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
We anticipate a total of six contributed talks of 20 minutes each, distributed
evenly over the following three high-level areas:
- Being data-driven.
o 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
o What is the role of online evaluation (e.g. as a benchmark?), and how would
we make it accessible to the general community?
o What can be done with simulated environments, or tasks where machines
communicate solely with each other?
- Build complete applications.
o Do we need to build a irreducible end-to-end system, or can we define
modules with abstractions that do not leak?
o How do we ease the burden on the human designer of specifying or
bootstrapping the system?
- Model innovation.
o What are the requisite capabilities for learning architectures, and where
are the deficiencies in our current architectures?
o How can we beneficially incorporate linguistic knowledge into our
The papers should be typeset according to NIPS 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.
- 10/09/2016: Submissions Due
- 10/23/2016: Acceptance Notification
- Hal Daume III
- Paul Mineiro
- Amanda Stent
- Jason Weston
Paper submission and more information : http://letsdiscussnips2016.weebly.com/
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list