Universal Semantic Parsing

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.

arXiv commentEMNLP 2017

Cited by in corpus (19)

• AMR Dependency Parsing with a Typed Semantic Algebra
• Towards Universal Semantic Tagging
• Learning to Paraphrase for Question Answering
• Exploiting Rich Syntactic Information for Semantic Parsing with Graph-to-Sequence Model
• Neural Networks for Cross-lingual Negation Scope Detection
• Cross-domain Semantic Parsing via Paraphrasing
• Building a Neural Semantic Parser from a Domain Ontology
• Simpler but More Accurate Semantic Dependency Parsing
• VASTA: A Vision and Language-assisted Smartphone Task Automation System
• Weakly-supervised Neural Semantic Parsing with a Generative Ranker
• SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases
• Dependency-based Hybrid Trees for Semantic Parsing
• Learning an Executable Neural Semantic Parser
• Exploring Probabilistic Soft Logic as a framework for integrating top-down and bottom-up processing of language in a task context
• Multimodal Interactive Learning of Primitive Actions
• On the Relation between Syntactic Divergence and Zero-Shot Performance
• EAT: a simple and versatile semantic representation format for multi-purpose NLP
• A survey of cross-lingual features for zero-shot cross-lingual semantic parsing
• Multilingual Neural Semantic Parsing for Low-Resourced Languages