Evaluating Induced CCG Parsers on Grounded Semantic Parsing

Yonatan Bisk1, Siva Reddy2, John Blitzer3, Julia Hockenmaier4, Mark Steedman2
1ISI/USC, 2University of Edinburgh, 3, 4University of Illinois Urbana-Champaign


Abstract

We compare the effectiveness of four different syntactic CCG parsers for a semantic slot-filling task to explore how much syntactic supervision is required for downstream semantic analysis. This extrinsic, task-based evaluation also provides a unique window into the semantics captured (or missed) by unsupervised grammar induction systems.