LbI18: Learning by Instruction Workshop at NIPS 2018 Palais des Congrès Montréal, Canada, December 8, 2018 |
Conference website | https://sites.google.com/view/lbi2018/ |
Submission link | https://easychair.org/conferences/?conf=lbi18 |
Submission deadline | November 9, 2018 |
Today machine learning is largely about statistical pattern discovery and function approximation from large volumes of data. But as computing devices that interact with us in natural language become ubiquitous (e.g., Siri, Alexa, Google Now), and as computer perceptual abilities become more accurate, they open an exciting possibility of enabling end-users to teach machines similar to the way in which humans teach one another. Natural language conversations, gesturing, demonstrations, teleoperation and other modes of communication offer a new paradigm for machine learning through instruction from humans. This builds on several existing machine learning paradigms (e.g., active learning, supervised learning, reinforcement learning), but also brings a new set of advantages and research challenges that lie at the intersection of several fields including machine learning, natural language understanding, computer perception, and HCI.
The aim of this workshop is to showcase new research in this area and to engage researchers and practitioners from these diverse fields to explore fundamental research questions such as:
- How do people interact with machines when teaching them new tasks and knowledge?
- What novel learning models and algorithms are needed to learn from human instruction?
- What are the practical and architectural considerations towards building computer systems that can learn from instruction?
Submission Guidelines
We invite paper submissions to our workshop on topics related to both practical and theoretical aspects of learning by instruction, including but not limited to the following areas:
- Learning from natural language explanations
- Learning by demonstrations
- Instruction-following and teleoperation
- Interactive learning
- Learning from multiple teachers
- Learning in grounded environments
- Effective techniques for incorporating human domain knowledge
- Persistent and iterative task learning from extended interactions
- Novel applications of learning by instruction
Please format your papers using NIPS 2018 style files. The page limit is 4-8 pages (excluding references). Previously published work (or under-review) is acceptable, though it needs to be indicated (in a footnote) as published work when submitting. Please indicate this as a footnote in the actual pdf indicating the venue where the work has been submitted. Accepted work will be presented as posters during the workshop, with exceptional submissions also presented as oral talks. Accepted papers will not be archived, thus submission does not preclude publications in other venues.
Committees
Organizing committee
- Shashank Srivastava
- Igor Labutov
- Bishan Yang
- Amos Azaria
- Tom Mitchell
Contact
All questions about submissions should be emailed to lbi2018nips@gmail.com