NLP is being revolutionized by deep learning with neural networks. However, deep learning requires large amounts of annotated data, and its advantage over traditional statistical methods typically diminishes when such data is not available. Even in high-resource languages, it can be difficult to find linguistically annotated data of sufficient size and quality to allow neural methods to excel. The workshop aims to bring together experts in deep learning and natural language processing whose research focuses on learning with scarce data. Specifically, it will provide attendees with an overview of existing approaches from various disciplines, and enable them to distill principles that can be more generally applicable. We will also discuss the main challenges arising in this setting and outline potential directions for future progress. The target audience consists of researchers and practitioners in related areas.
Topics of Interest:
==
Active learning
Transfer learning
Multi-task learning
Few-shot learning
Learning-to-Learn and Meta-Learning
Semi-supervised learning
Dual learning
Unsupervised learning
Bandit/Reinforcement learning to learn from weak/sparse supervision Domain adaptation
Decipherment or zero-shot learning
Language projections
Universal representations and interlinguas
Low resource structured prediction
Submission Guidelines:
==
Please submit your paper using START:
https://www.softconf.com/emnlp2019/ws-DeepLo2019/
Submissions must be in PDF format, anonymized for review, written in English and follow the EMNLP 2019 formatting requirements, available here:
https://www.emnlp-ijcnlp2019.org/calls/papers
We strongly advise you use the LaTeX template files provided by EMNLP 2019.
Submissions consist of up to eight pages of content. There is no limit on the number of pages for references. There is no extra space for appendices. Accepted papers will be given one additional page for content.
Authors can also submit non-archival papers of up to eight pages of content. Non-archival papers will not be included in the proceedings. Thus, your work will retain the status of being unpublished and later submission at another venue (e.g., a journal) is not precluded. Likewise, you are free to re-present work that has been previously published elsewhere.
We anticipate most papers, both archival and non-archival, will be presented as posters and spotlight presentation, with only a few selected for contributed talks.
Tentative Program:
==
The program consists of 5 invited talks, spotlight presentations, contributed talks, and poster presentations of submitted papers.
Invited Talks:
==
Heng Ji (University of Illinois Urbana-Champaign)
Barbara Plank (IT University of Copenhagen)
Dan Roth (University of Pennsylvania)
Kristina Toutanova (Google AI Language)
Luke Zettlemoyer (University of Washington / Facebook AI Research)
Organizers:
==
Colin Cherry - Google
Greg Durrett - University of Texas, Austin
George Foster - Google
Gholamreza (Reza) Haffari - Monash University
Shahram Khadivi - eBay
Nanyun Peng - University of Southern California
Xiang Ren - University of Southern California
Swabha Swayamdipta - Allen Institute of Artificial Intelligence