Evaluating Induced CCG Parsers on Grounded Semantic Parsing

September 29, 2016 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 8.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .classpath, .gitignore, .project, .pydevproject, AUTHORS, LICENSE, Makefile, Makefile.easysrl, Makefile.induction, Makefile.par, Makefile.tacl2014, Makefile.uw, OWNERS, README.md, build.xml, commands.sh, data, input.txt, install.py, lib_data, reinforce.mk, run.sh, scripts, src, test, test_data

Authors Yonatan Bisk, Siva Reddy, John Blitzer, Julia Hockenmaier, Mark Steedman arXiv ID 1609.09405 Category cs.CL: Computation & Language Cross-listed cs.AI Citations 17 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/sivareddyg/graph-parser ⭐ 123 Last Checked 2 months ago

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.