UncertaiNLP 2024 : First Workshop on Uncertainty-Aware NLP @ EACL 2024
Call For Papers
First Call for papers: UncertaiNLP - First Workshop on Uncertainty-Aware NLP @ EACL 2024, March 21 or 22, 2024
Submission website: https://openreview.net/group?id=eacl.org/EACL/2024/Workshop/UncertaiNLP
We invite submissions to the first edition of the UncertaiNLP workshop on Uncertainty-Aware NLP, to be held at EACL 2024 on March 21 or 22, 2024.
Paper submission deadline: December 18, 2023
Resubmission of already pre-reviewed ARR papers: January 17, 2024
Notification of acceptance: January 20, 2024
Camera-ready papers due: January 30 2024
Workshop dates: March 21-22, 2024
Human languages are inherently ambiguous and understanding language input is subject to interpretation and complex contextual dependencies. Nevertheless, the main body of research in NLP is still based on the assumption that ambiguities and other types of underspecification can and have to be resolved. This workshop will provide a platform for research that embraces variability in human language and aims to represent and evaluate the uncertainty that arises from it, and from modeling tools themselves.
[Topics of Interest]
UncertaiNLP welcomes submissions to topics related (but not limited) to:
Frameworks for uncertainty representation
Theoretical work on probability and its generalizations
Symbolic representations of uncertainty
Documenting sources of uncertainty
Theoretical underpinnings of linguistic sources of variation
Data collection (e.g., to document linguistic variability, multiple perspectives, etc.)
Explicit representation of model uncertainty (e.g., parameter and/or hypothesis uncertainty, Bayesian NNs in NLU/NLG, verbalised uncertainty, feature density, external calibration modules)
Disentangled representation of different sources of uncertainty (e.g., hierarchical models, prompting)
Reducing uncertainty due to additional context (e.g., additional context, clarification questions, retrieval/API augmented models)
Learning (or parameter estimation)
Learning from single and/or multiple references
Gradient estimation in latent variable models
Theoretical and applied work on approximate inference (e.g., variational inference, Langevin dynamics)
Unbiased and asymptotically unbiased sampling algorithms
Utility-aware decoders and controllable generation
Statistical evaluation of language models
Calibration to interpretable notions of uncertainty (e.g., calibration error, conformal prediction)
Evaluation of epistemic uncertainty
Authors are invited to submit by December 18, 2023 original and unpublished research papers in the following categories:
Full papers (up to 8 pages) for substantial contributions.
Short papers (up to 4 pages) for ongoing or preliminary work.
All submissions must be in PDF format, submitted electronically via OpenReview (https://openreview.net/group?id=eacl.org/EACL/2024/Workshop/UncertaiNLP) and should follow the EACL 2024 formatting guidelines (following the ARR CfP: use the official ACL style templates, which are available here).
We also invite authors of papers accepted to Findings to reach out to the organizing committee of UncertaiNLP to present their papers at the workshop, if in line with the topics described above. Resubmission of already pre-reviewed ARR papers will be possible and more information will be sent in the later calls.
Wilker Aziz, University of Amsterdam
Joris Baan, University of Amsterdam
Hande Celikkanat, University of Helsinki
Marie-Catherine de Marneffe, UCLouvain/FNRS
Barbara Plank, LMU Munich
Swabha Swayamdipta, USC
Jörg Tiedemann, University of Helsinki
Dennis Ulmer, ITU Copenhagen
A list of program committee members will be available on the workshop website.
For inquiries, please contact firstname.lastname@example.org