The fifth edition of BlackboxNLP 2022 will be collocated with EMNLP 2022. A reminder that our upcoming submission deadline for papers and extended abstracts that do not have ARR reviews is September 7th.
Workshop description
Many recent performance improvements in NLP have come at the cost of understanding of the systems. How do we assess what representations and computations models learn? How do we formalize desirable properties of interpretable models, and measure the extent to which existing models achieve them? How can we build models that better encode these properties? What can new or existing tools tell us about systems’ inductive biases?
The goal of this workshop is to bring together researchers focused on interpreting and explaining NLP models by taking inspiration from machine learning, psychology, linguistics, and neuroscience. We hope the workshop will serve as an interdisciplinary meetup that allows for cross-collaboration.
The topics of the workshop include, but are not limited to:
- Explanation methods such as saliency, attribution, free-text explanations, or explanations with structured properties
- Probing methods for testing whether models have acquired or represent certain linguistic properties
- Applying analysis techniques from other disciplines (e.g., neuroscience or computer vision)
- Examining model performance on simplified or formal languages
- More interpretable model architectures
- Open-source tools for analysis, visualization, or explanation;
- Evaluation of explanation methods
- Opinion pieces about the state of explainable NLP
Feel free to reach out to the organizers at the email below if you are not sure whether a specific topic is well-suited for submission.
Important Dates
- September 7, 2022 -- Direct submission deadline (via OpenReview: https://openreview.net/group?id=EMNLP/2022/Workshop/BlackboxNLP).
- October 2, 2022 -- ARR commitment deadline (via OpenReview: https://openreview.net/group?id=EMNLP/2022/Workshop/BlackboxNLP).
- October 9, 2022 -- Notification of acceptance.
- October 16, 2022 -- Camera-ready papers due.
- December 8, 2022 -- Workshop (hybrid).
All deadlines are 11:59pm UTC-12 (anywhere on earth).
Call for Papers
All submissions should use the ACL templates (https://github.com/acl-org/acl-style-files) and formatting requirements specified by ACL Rolling Review, and should be fully anonymized. Submissions of both types can be made through
OpenReview at https://openreview.net/group?id=EMNLP/2022/Workshop/BlackboxNLP.
Submission Types
- Archival papers of up to 8 pages + references. These are papers reporting on completed, original and unpublished research, and can be submitted either with or without ARR reviews by selecting the appropriate box on the submission form. An optional appendix may appear after the references in the same pdf file. If you do not include ARR reviews with your submission, it will be reviewed by reviewers specific to the BlackBoxNLP workshop. Accepted papers are expected to be presented at the workshop and will be published in the workshop proceedings of the ACL Anthology, meaning they cannot be published elsewhere. They should report on obtained results rather than intended work.
- Non-archival extended abstracts of 2 pages + references. These may report on work in progress or may be cross submissions of work that has already appeared (or is scheduled to appear) in another venue in 2021-2022. Abstract titles will be posted on the workshop website but will not be included in the proceedings.
Contact
More information can be found on the website: https://blackboxnlp.github.io/
Please contact the organizers at blackboxnlp [at] googlegroups.com for any questions.
Organizers
Jasmijn Bastings, Google
Yonatan Belinkov, Technion
Yanai Elazar, Allen Institute for Artificial Intelligence & University of Washington
Dieuwke Hupkes, Facebook AI Research
Naomi Saphra, New York University
Sarah Wiegreffe, Allen Institute for Artificial Intelligence
BlackboxNLP 2022 adheres to the ACL Anti-Harassment Policy: https://www.aclweb.org/adminwiki/index.php?title=Anti-Harassment_Policy.