(Apologies for cross-post) NeurIPS 2019 - Workshop on ‘Context and Compositionality in biological and artificial neural systems’ Vancouver Convention Center, Vancouver CANADA Fri Dec 13th or Sat Dec 14th https://context-composition.github.io <https://context-composition.github.io/> Workshop abstract: The ability to integrate semantic information across narratives is fundamental to language understanding in both biological and artificial cognitive systems. There have been enormous strides in NLP and Machine Learning to develop architectures and techniques that effectively capture these effects. We have moved away from traditional bag-of-words approaches that ignore temporal ordering to RNNs, Temporal CNNs and Transformers that incorporate contextual information at varying timescales. While these architectures have lead to SoTA performance on many difficult language understanding tasks, it is unclear what representations these networks learn and how exactly they incorporate context. Interpreting these networks, systematically analyzing the advantages and disadvantages of different elements, such as gating or attention, and reflecting on the capacity of the networks across various timescales are open and important questions. On the biological side, recent work in neuroscience suggests that areas in the brain are organized into a temporal hierarchy in which different areas are not only sensitive to specific semantic information but also to the composition of information at different timescales. Computational neuroscience has moved in the direction of leveraging deep learning to gain insights about the brain. By answering questions on the underlying mechanisms and representational interpretability of these artificial networks, we can also expand our understanding of temporal hierarchies, memory and capacity effects in the brain. In this workshop we aim to bring together researchers from machine learning, NLP, and neuroscience to explore and discuss how computational models should effectively capture the multi-timescale, context-dependent effects that seem essential for processes such as language understanding. We believe that this will not only lead to a deeper understanding of biological language systems but also better artificial systems that can leverage these insights and understand language better. Call For Papers Paper submission deadline: Mon September 9th, 2019 22:00 PM UTC Decision Notification: Sun September 29th, 2019 22:00 PM UTC Submit at: https://cmt3.research.microsoft.com/CNTXTCOMP2019/ <https://cmt3.research.microsoft.com/CNTXTCOMP2019/> The site will start accepting submissions on August 7th. We invite paper submissions on the following topics, or any related or relevant work: • Contextual sequence processing in the human brain • Compositional representations in the human brain • Systematic generalization in deep learning • Compositionality in human intelligence • Compositionality in natural language • Understanding composition and temporal processing in neural network models • New approaches to compositionality and temporal processing in language • Hierarchical representations of temporal information • Datasets for contextual sequence processing • Applications of compositional neural networks to real-world problems Formatting Instructions: All submissions must be in PDF format. Submissions are limited to four content pages, including all figures and tables; additional pages containing only references are allowed. You must format your submission using the NeurIPS 2019 LaTeX style file. Submissions that violate the NeurIPS style (e.g., by decreasing margins or font sizes) or page limits may be rejected without further review. All submissions should be anonymous. Accepted papers will be presented during a poster session, with spotlight oral presentations for exceptional submissions. The accepted papers will be made publicly available as non-archival reports, allowing future submissions to archival conferences or journals. The review process is double-blind. We also welcome published papers that are within the scope of the workshop (without re-formatting, if the paper is already 4 pages or shorter). Already-published papers do not need to be anonymous. They are eligible for poster sessions and will only have a very light review process. Please redirect questions and all future correspondence to shaileejain@utexas.edu <mailto:shaileejain@utexas.edu>. Workshop Organizing Committee Javier Turek, Alexander Huth, Shailee Jain, Christopher Honey, Tal Linzen, Leila Wehbe, Emma Strubell, Kyunghyun Cho and Alan Yuille -- ALEXANDER G. HUTH, PhD | Assistant Professor The University of Texas at Austin Departments of Computer Science & Neuroscience