Universal Meaning Representation Format for Natural Language Task Engines. Valner, R., Wanna, S., & Pryor, M. In Macau, China, October, 2019.
Universal Meaning Representation Format for Natural Language Task Engines [link]Paper  abstract   bibtex   14 downloads  
In order to rapidly deploy natural language interfaces for robotics applications, we developed the Universal Meaning Representation Format (UMRF) and TeMoto Action Engine. The proposed UMRF acts as a middle ground for combining existing and cutting edge solutions in the domains of natural language processing and grounding. The open-sourced TeMoto Action Engine offers developers an UMRF based action execution management system to use as an interface for natural language control, via grounding the UMRF data structures to executable code. We demonstrate the feasibility of the developed work by executing robotic tasks on ROS via different parsing systems, including Google Assistant.
@inproceedings{valner_universal_2019,
	address = {Macau, China},
	title = {Universal {Meaning} {Representation} {Format} for {Natural} {Language} {Task} {Engines}},
	url = {https://roscon.ros.org/2019/},
	abstract = {In order to rapidly deploy natural language interfaces for robotics applications, we developed the Universal Meaning Representation Format (UMRF) and TeMoto Action Engine. The proposed UMRF acts as a middle ground for combining existing and cutting edge solutions in the domains of natural language processing and grounding. The open-sourced TeMoto Action Engine offers developers an UMRF based action execution management system to use as an interface for natural language control, via grounding the UMRF data structures to executable code. We demonstrate the feasibility of the developed work by executing robotic tasks on ROS via different parsing systems, including Google Assistant.},
	author = {Valner, Robert and Wanna, Selma and Pryor, Mitch},
	month = oct,
	year = {2019},
}

Downloads: 14