splu-robonlp.github.io - SpLU-RoboNLP 2019

Example domain paragraphs

SpLU-RoboNLP 2019 is a combined workshop on spatial language understanding (SpLU) and grounded communication for robotics (RoboNLP) that focuses on spatial language, both linguistic and theoretical aspects and its application to various areas including and especially focusing on robotics. The combined workshop aims to bring together members of NLP, robotics, vision and related communities in order to initiate discussions across fields dealing with spatial language along with other modalities. The desired ou

While language can encode highly complex, relational structures of objects, spatial relations between them, and patterns of motion through space, the community has only scratched the surface on how to encode and reason about spatial semantics. Despite this, spatial language is crucial to robotics, navigation, NLU, translation and more. Standardizing tasks is challenging as we lack formal domain independent meaning representations. Spatial semantics requires an interplay between language, perception and (oft

Following the exciting recent progress in visual language grounding, the embodied, task-oriented aspect of language grounding is an important and timely research direction. To realize the long-term goal of robots that we can converse with in our homes, offices, hospitals, and warehouses, it is essential that we develop new techniques for linking language to action in the real world in which spatial language understanding plays a great role. Can we give instructions to robotic agents to assist with navigatio

Links to splu-robonlp.github.io (6)