*Call for Papers* *The 1st workshop on Simple and Efficient Natural Language Processing (SustaiNLP)*
*Location:* *Virtual* (co-located with EMNLP 2020) *Date:* Wednesday, 11 November 2020 *Contact: * sustainlp-2...@googlegroups.com *Website: * https://sites.google.com/view/sustainlp2020 *Submission Deadline:* Sunday, 30 August 2020 The 1st Workshop on Simple and Efficient Natural Language Processing (SustaiNLP 2020) will be co-located with EMNLP2020 and will be held virtually on November 11, 2020. 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. *INVITED SPEAKERS* We are pleased to announce the following invited speakers: Mona Diab Heng Ji Graham Neubig Alexander Rush Emma Strubell Armand Joulin *PANEL* We will also hold a moderated panel discussion with our invited speakers as well as the following panelists: Kyunghyun Cho Yejin Choi Yoav Goldberg Iryna Gurevych *TOPICS OF INTEREST* 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 *IMPORTANT DATES* Anonymity period begins: July 30, 2020 Submission deadline: August 30, 2020 Notification of acceptance: September 29, 2020 Camera-ready papers due: October 10, 2020 Workshop: November 11, 2020 All deadlines are 11.59 pm UTC -12h (“anywhere on Earth”). *SUBMISSIONS* Submission is electronic, using the Softconf START conference management system. Submission link: https://www.softconf.com/emnlp2020/sustainlp2020/ Both long and short papers must follow the EMNLP 2020 style file: https://2020.emnlp.org/files/emnlp2020-templates.zip We solicit three categories of papers: - Standard workshop papers: anonymized submissions describing substantially original research not previously published in other venues. - Extended abstracts: anonymized submissions describing preliminary but interesting ideas or results not previously published in other venues. - Cross-submissions: non-anonymized papers on relevant topics that have previously been accepted for publication in another venue. Only standard workshop papers will be included in the proceedings as archival publications. All three categories of papers may be long (maximum 8 pages plus references) or short (maximum 4 pages plus references). Supplementary Material: Each submission can be accompanied by a single PDF appendix. The paper submissions need to remain fully self-contained, as these supplementary materials are completely optional, and reviewers are not even asked to review or download them. Supplementary materials need to be fully anonymized to preserve the double-blind reviewing policy. For more information on the SustaiNLP workshop, please visit https://sites.google.com/view/sustainlp2020/. *SHARED TASK* We are also organizing a shared task to promote the development of effective, energy-efficient models for difficult NLU tasks. The shared task is centered around the SuperGLUE benchmark (https://super.gluebenchmark.com/), which tests a system’s performance across a diverse set of eight NLU tasks. In addition to the standard SuperGLUE performance metrics, the shared task will evaluate the energy consumption of each submission while processing the test data. For more information on the SustaiNLP shared task, please visit https://sites.google.com/view/sustainlp2020/shared-task. *ORGANIZING COMMITTEE* Angela Fan, LORIA and Facebook AI Research Paris Goran Glavaš, University of Mannheim Shafiq Joty, Nanyang Technological University, Singapore Nafise Sadat Moosavi, University of Darmstadt Vered Shwartz, Allen Institute for AI (AI2) and the University of Washington Alex Wang, New York University Thomas Wolf, Huggingface Inc. Sam Bowman, New York University
_______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
