Abstract
The interpretation of spatial references is highly contextual, requiring joint inference over both language and the environment. We consider the task of spatial reasoning in a simulated environment, where an agent can act and receive rewards. The proposed model learns a representation of the world steered by instruction text. This design allows for precise alignment of local neighborhoods with corresponding verbalizations, while also handling global references in the instructions. We train our model with reinforcement learning using a variant of generalized value iteration. The model outperforms state-of-the-art approaches on several metrics, yielding a 45% reduction in goal localization error.
Highlights
Understanding spatial references in natural language is essential for successful human-robot communication and autonomous navigation
We assume access to a simulated environment, in which an agent can take actions to interact with the world and is rewarded for reaching the location specified by the language instruction
Task setup We model our task as a Markov Decision Process (MDP), where an autonomous agent is placed in an interactive environment with the capability to choose actions that can affect the world
Summary
Understanding spatial references in natural language is essential for successful human-robot communication and autonomous navigation. This problem is challenging because interpretation of spatial references is highly context-dependent. We explore the problem of spatial reasoning in the context of interactive worlds. We assume access to a simulated environment, in which an agent can take actions to interact with the world and is rewarded for reaching the location specified by the language instruction. This feedback is the only source of supervision the model uses for interpreting spatial references
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Transactions of the Association for Computational Linguistics
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
