PrivateNLP'20: WSDM 2020 Workshop on Privacy and Natural Language Processing Colocated with WSDM 2020 Houston, TX, United States, February 7, 2020 |
Conference website | https://sites.google.com/view/wsdm-privatenlp-2020 |
Submission link | https://easychair.org/conferences/?conf=privatenlp20 |
Poster | download |
Abstract registration deadline | November 30, 2019 |
Submission deadline | December 15, 2019 |
Acceptance Notification | December 27, 2019 |
Camera-ready versions | January 10, 2020 |
Privacy-preserving data analysis has become essential in the age of Machine Learning (ML) where access to vast amounts of data can provide gains over tuned algorithms. A large proportion of user-contributed data comes from natural language e.g., text transcriptions from voice assistants.
It is therefore important to curate NLP datasets while preserving the privacy of the users whose data is collected, and train ML models that only retain non-identifying user data.
The workshop aims to bring together practitioners and researchers from academia and industry to discuss the challenges and approaches to designing, building, verifying, and testing privacy preserving systems in the context of Natural Language Processing.
Submission Guidelines
All submissions will be double-blind peer reviewed (with author names and affiliations removed) by the program committee and judged by their relevance to the workshop themes. All submissions must be in English, formatted according to the latest 2 column ACM SIG proceedings template.
Submitted manuscripts must be 8 pages long for full papers, and 4 pages long for short papers. Both full and short papers can have 2 additional pages for references and appendices. Extended abstracts / posters must be 2 pages. Please note that at least one of the authors of each accepted paper must register for the workshop and present the paper in-person.
Submissions should be made as a pdf file to: https://easychair.org/conferences/?conf=privatenlp20
List of Topics
Topics of interest include but are not limited to:
- Generating privacy preserving test sets
- Inference and identification attacks
- Generating Differentially private derived data
- NLP, privacy and regulatory compliance
- Private Generative Adverserial Networks
- Privacy in Active Learning and Crowdsourcing
- Privacy and Federated Learning in NLP
- User perceptions on privatized personal data
- Auditing provenance in language models
- Continual learning under privacy constraints
- NLP and summarization of privacy policies
- Ethical ramifications of AI/NLP in support of usable privacy
Committees
Organizing committee
- Oluwaseyi Feyisetan (Amazon, USA)
- Sepideh Ghanavati (University of Maine, USA)
- Oleg Rokhlenko (Amazon, USA)
- Patricia Thaine (University of Toronto, Canada)
Program Committee
- Aleksei Triastcyn (École Polytechnique Fédérale de Lausanne)
- Andreas Nautsch (EURECOM)
- Arne Köhn (Saarland University)
- Avi Arampatzis (Democritus University of Thrace)
- Asma Eidhah Aloufi (Rochester Institute of Technology)
- Benjamin Zi Hao Zhao (University of New South Wales)
- Borja Balle (DeepMind)
- Claire McKay Bowen (Los Alamos National Laboratory)
- Congzheng Song (Cornell)
- Dinusha Vatsalan (Data61-CSIRO)
- Elette Boyle (IDC Herzliya)
- Fang Liu (University of Notre Dame)
- Isar Nejadgholi (National Research Council Canada)
- Jamie Hayes (University College London)
- Jason Xue (University of Adelaide)
- Julius Adebayo (MIT)
- Kambiz Ghazinour (State University of New York)
- Liwei Song (Princeton)
- Luca Melis (Amazon USA)
- Mark Dras (Macquarie University)
- Maximin Coavoux (University of Edinburgh)
- Mitra Bokaei Hosseini (St. Mary's University)
- Natasha Fernandes (Macquarie University)
- Nedelina Teneva (Amazon USA)
- Olya Ohrimenko (Microsoft Research)
- Pauline Anthonysamy (Google)
- Sai Teja Peddinti (Google)
- Shomir Wilson (Pennsylvania State University)
- Tom Diethe (Amazon UK)
- Travis Breaux (Carnegie Mellon University)
Publication
PrivateNLP'20 proceedings will be by CEUR-WS
Venue
The conference will be held in Houston, Texas, colocated with WSDM 2020
Contact
All questions about submissions should be emailed to: privatenlp-wsdm@googlegroups.com