Abstract

People use verbal descriptions to communicate spatial information, externalising relevant parts of their mental spatial representations. In many situations, such as emergency response, the ability of a machine to interpret these verbal descriptions could assist in human-machine interaction. As a first step in such an endeavor, this paper presents an automatic approach that translates spatial objects and their spatial relations extracted from verbal descriptions via natural language processing into a plausible sketch map. The proposed methodology applies a hierarchical and dynamic sketch map drawing strategy that is inspired by heuristics people apply in their interpretation of place descriptions, in order to accommodate underspecifying, flexible and conflicting common language. The methodology is implemented and tested. This article ends with some insights for further research towards automatic interpretation of verbal place descriptions.

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 call

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.