Universal Semantic Parsing

February 10, 2017 · Entered Twilight · 🏛 Conference on Empirical Methods in Natural Language Processing

"Last commit was 7.0 years ago (≥5 year threshold)"

Evidence collected by the PWNC Scanner

Repo contents: .classpath, .gitignore, .gitmodules, .project, .pydevproject, CONTRIBUTING.md, LICENSE, Makefile, README.md, build.xml, data, datarelease.mk, debug.txt, doc, gq.mk, input-english.txt, input-german.txt, input-spanish.txt, lib, lib_data, protos, run-english.sh, run-german.sh, run-spanish.sh, scripts, servlets, src, test

Authors Siva Reddy, Oscar Täckström, Slav Petrov, Mark Steedman, Mirella Lapata arXiv ID 1702.03196 Category cs.CL: Computation & Language Citations 110 Venue Conference on Empirical Methods in Natural Language Processing Repository https://github.com/sivareddyg/udeplambda ⭐ 91 Last Checked 1 month ago

Abstract

Universal Dependencies (UD) offer a uniform cross-lingual syntactic representation, with the aim of advancing multilingual applications. Recent work shows that semantic parsing can be accomplished by transforming syntactic dependencies to logical forms. However, this work is limited to English, and cannot process dependency graphs, which allow handling complex phenomena such as control. In this work, we introduce UDepLambda, a semantic interface for UD, which maps natural language to logical forms in an almost language-independent fashion and can process dependency graphs. We perform experiments on question answering against Freebase and provide German and Spanish translations of the WebQuestions and GraphQuestions datasets to facilitate multilingual evaluation. Results show that UDepLambda outperforms strong baselines across languages and datasets. For English, it achieves a 4.9 F1 point improvement over the state-of-the-art on GraphQuestions. Our code and data can be downloaded at https://github.com/sivareddyg/udeplambda.