Aim and Scope
Leveraging the foundation built in the prior workshops RoboNLP 2017, SpLU 2018, SpLU-RoboNLP 2019, and SpLU 2020, this workshop aims to realize the long-term goal of natural conversation with machines in our homes, workplaces, hospitals, and warehouses. It also highlights the importance of spatial semantics when it comes to communicating about the physical world and grounding language in perception. Human-robot dialogue often involves developing an understanding of grounded spatial descriptions. These capabilities invariably require understanding spatial semantics that relates to the physical environments where robots are embodied. The main goal of this joint workshop is to bring in the perspectives of researchers working on physical robot systems and with human users, and align spatial language understanding representation and learning approaches, datasets, and benchmarks with the goals and constraints encountered in HRI and robotics. Such constraints include high costs of real-robot experiments, human-in-the-loop training and evaluation settings, scarcity of embodied data, as well as non-verbal communication.Topics of Interest
- Achieving Common Ground in Human-Robot Interaction
- Aligning and Translating Language to Situated Actions
- Cognitive and Linguistically Motivated Spatial Language Representations
- Evaluation Metrics for Language Grounding and Human-Robot Communication
- Human-Computer Interactions Through Natural or Structural Language
- Instruction Understanding and Spatial Reasoning Based on Multimodal Information for Navigation, Articulation, and Manipulation
- Interactive Situated Dialogue for Physical Tasks
- Language-based Game Playing for Grounding
- Reasoning over Spatial Language (e.g. Based on Qualitative and Quantitative Spatial Representation)
- Spatial Language and Skill Learning via Grounded Dialogue
- Spatial Information Extraction from Text (e.g. Locative Descriptions, Navigation Instruction)
- (Spatial) Language Generation for Embodied Tasks
- (Spatially) Grounded Knowledge Representations
Invited Speakers
- Maja Matarić, University of Southern California
- Kartik Narasimhan, Princeton University
- Jean Oh, Carnegie Mellon University
- Thora Tenbrink, Bangor University
Submissions
Long Papers
Technical papers: ACL style, 8 pages excluding references
Short Papers
Position statements describing previously unpublished work or demos: ACL style, 4 pages excluding references
ACL Style files: Template
Submissions website: Softconf
Important Dates
- Submission Deadline: April 26, 2021
- Notification: May 28, 2021
- Camera Ready Deadline: June 7, 2021
- Workshop Day: August 5-6, 2021
Organizing Committee
University of Pittsburgh | malihe@pitt.edu | |
Cornell University | valts@cs.cornell.edu | |
Michigan State University | kordjams@msu.edu | |
Amazon Alexa AI | padmakua@amazon.com | |
University of North Carolina | haotan@cs.unc.edu |
Program Committee
University of Rochester | |
Tel-Aviv University | |
University of Arizona | |
University of Groningen | |
Carnegie Mellon University | |
KU Leuven | |
University of Gothenburg, Sweden | |
KTH Royal Institute of Technology | |
University of Maryland, Baltimore County | |
University of California, Berkeley | |
Tufts University | |
Australian National University | |
Stanford University | |
Inria | |
University of Washington | |
Stanford University | |
UNC Chapel Hill | |
Oregon State University | |
Army Research Laboratory | |
ByteDance AI Lab | |
Michigan State University | |
University of Texas, Austin | |
Microsoft | |
University of Illinois, Chicago | |
NVIDIA | |
Brown University | |
University of Maryland, Baltimore County | |
University of Michigan | |
University of Texas, Houston | |
University of California, Berkeley | |
University of Washington | |
Georgia Tech | |
Tufts University | |
Massey University of New Zealand | |
Cornell University | |
University of Washington | |
Columbia University | |
University of California, Santa Cruz | |
SUNY Binghamton |