UW-MRS: Leveraging a Deep Grammar for Robotic Spatial Commands

Abstract

This paper describes a deep-parsing ap-proach to SemEval-2014 Task 6, a novel context-informed supervised parsing and semantic analysis problem in a controlled domain. The system comprises a hand-built rule-based solution based on a pre-existing broad coverage deep grammar of English, backed up by a off-the-shelf data-driven PCFG parser, and achieves the best score reported among the task participants. 1