Universal Semantic Parsing

TL;DR

This paper introduces UDepLambda, a multilingual semantic parser that converts Universal Dependencies into logical forms, effectively handling complex linguistic phenomena across languages and outperforming existing methods on question answering tasks.

Contribution

UDepLambda is a novel semantic interface that processes dependency graphs and is nearly language-independent, advancing multilingual semantic parsing capabilities.

Findings

Outperforms strong baselines across multiple languages and datasets.

Achieves a 4.9 F1 point improvement over the state-of-the-art on GraphQuestions for English.

Supports multilingual evaluation with German and Spanish datasets.

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.