Universal semantic parsing

60Citations
Citations of this article
244Readers
Mendeley users who have this article in their library.

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.

Cite

CITATION STYLE

APA

Reddy, S., Täckström, O., Petrov, S., Steedman, M., & Lapata, M. (2017). Universal semantic parsing. In EMNLP 2017 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 89–101). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/d17-1009

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free