Evaluating Induced CCG Parsers on Grounded Semantic Parsing
Computation and Language
2017-02-01 v2 Artificial Intelligence
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 provides a unique window to explore the strengths and weaknesses of semantics captured by unsupervised grammar induction systems. We release a new Freebase semantic parsing dataset called SPADES (Semantic PArsing of DEclarative Sentences) containing 93K cloze-style questions paired with answers. We evaluate all our models on this dataset. Our code and data are available at https://github.com/sivareddyg/graph-parser.
Keywords
Cite
@article{arxiv.1609.09405,
title = {Evaluating Induced CCG Parsers on Grounded Semantic Parsing},
author = {Yonatan Bisk and Siva Reddy and John Blitzer and Julia Hockenmaier and Mark Steedman},
journal= {arXiv preprint arXiv:1609.09405},
year = {2017}
}
Comments
EMNLP 2016, Table 2 erratum, Code and Freebase Semantic Parsing data URL