The 3rd Workshop on Simple and Efficient Natural Language Processing (SustaiNLP 2022) will be co-located with EMNLP2022 and will be held virtually on December 7, 2022.
------------------------------
Important Dates
------------------------------
- Latest ARR submission deadline: July 15, 2022
- Commitment deadline: October 2, 2022
- Notification of acceptance: October 25, 2022
- Camera-ready papers due: November 16, 2022
- Uploading pre-recorded videos to underline: November 16, 2022
- Workshop: December 7, 2022
All deadlines are 11:59 pm UTC -12h (“anywhere on Earth”)
------------------------------
Motivation
------------------------------
The NLP community in recent years focuses on improving performance on standard benchmarks, predominantly using neural models. While it has led to progress on various tasks, it also resulted in a worrisome increase in model complexity and the amount of computational resources required for training and using current state-of-the-art models. Moreover, the recent research efforts have, for the most part, failed to identify sources of empirical gains in models, failing to justify the model complexity beyond benchmark performance. In this context, the SustaiNLP workshop has two main objectives: (1) encouraging development of more efficient NLP models; and (2) providing simpler architectures and empirical justification of model complexity.
------------------------------
Topics of Interests
------------------------------
We encourage submissions in the following topics, including but are not limited to:
Models that yield competitive performance but require less training data, less computational resources, or less training time
Models with lower computational complexity of prediction/inference
Theoretical or empirical justification of the complexity of existing NLP models, e.g., by showing that meaningful simplifications of the model lead to significant deterioration in performances, interpretability, and/or robustness;
Conceptual or practical simplification of an existing model, yielding comparable performance, while offering advantages like interpretability, inference time, robustness, etc.
Suggesting new best practices in reporting experimental results
Critically analyzing existing evaluation protocols
Suggesting new evaluation protocols
------------------------------
Submissions
------------------------------
We only accept papers that are reviewed by ARR. The last possible ARR deadline for EMNLP workshop papers is July 15. Papers that have ARR meta-reviews can be committed to SustaiNLP by October 2nd. Please submit your paper via the following link: https://openreview.net/group?id=EMNLP/2022/Workshop/SustaiNLP
------------------------------
Invited Speakers
------------------------------
Song Han (MIT)
Kurt Keutzer (UC Berkeley)
Percy Liang (Stanford University)
Hinrich Schutze (University of Munich)
------------------------------
Panel Discussion
------------------------------
Invited Speakers and
Sam Bowman (New York University)
Barbara Plank (University of Munich)
Luke Zettlemoyer (University of Washington and Facebook AI Research)
------------------------------
Contact
Email: sustainlp-2022 [at] googlegroups.com
Website: https://sites.google.com/view/sustainlp2022
------------------------------
Organizers:
Nafise Sadat Moosavi (University of Sheffield)
Iryna Gurevych (Technical University of Darmstadt)
Angela Fan (INRIA Nancy and Facebook AI Research Paris)
Yufang Hou (IBM Research)
Zornitsa Kozareva (Facebook AI Research)
Sujith Ravi (SliceX AI)
Sasha Luccioni (MILA)
Gyuwan Kim (University of California, Santa Barbara)
Andreas Rücklé (Amazon Search Berlin)
Roy Schwartz (The Hebrew University of Jerusalem)