The GRUVE challenge: generating routes under uncertainty in virtual environments

Authors:
Srini Janarthanam;Oliver Lemon
Affiliations:
MACS, Heriot-Watt University Edinburgh, United Kingdom;MACS, Heriot-Watt University Edinburgh, United Kingdom
Venue:
ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
Year:
2011

Citing 5
Cited 2

Pedestrian navigation aids: information requirements and design implications

Personal and Ubiquitous Computing
Generation under uncertainty

INLG '10 Proceedings of the 6th International Natural Language Generation Conference
Generating adaptive route instructions using hierarchical reinforcement learning

SC'10 Proceedings of the 7th international conference on Spatial cognition
Hierarchical reinforcement learning and hidden Markov models for task-oriented natural language generation

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
Optimising natural language generation decision making for situated dialogue

SIGDIAL '11 Proceedings of the SIGDIAL 2011 Conference

Report on the second second challenge on generating instructions in virtual environments (GIVE-2.5)

ENLG '11 Proceedings of the 13th European Workshop on Natural Language Generation
A web-based evaluation framework for spatial instruction-giving systems

ACL '12 Proceedings of the ACL 2012 System Demonstrations

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a shared task based around generation of instructions for pedestrian users navigating in open-world virtual environments. An important variant of this task involves handling uncertainty about the user's location (as would happen in the real world with a standard GPS system). We motivate and explain the task, propose metrics for evaluation of systems, describe the planned software setup, and propose a timeline for the challenge.