Dependency-based Hybrid Trees for Semantic Parsing

Abstract

We propose a novel dependency-based hybrid tree model for semantic parsing, which converts natural language utterance into machine interpretable meaning representations. Unlike previous state-of-the-art models, the semantic information is interpreted as the latent dependency between the natural language words in our joint representation. Such dependency information can capture the interactions between the semantics and natural language words. We integrate a neural component into our model and propose an efficient dynamic-programming algorithm to perform tractable inference. Through extensive experiments on the standard multilingual GeoQuery dataset with eight languages, we demonstrate that our proposed approach is able to achieve state-of-the-art performance across several languages. Analysis also justifies the effectiveness of using our new dependency-based representation.

arXiv commentAccepted by EMNLP 2018

References in corpus (11)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Polyglot: Distributed Word Representations for Multilingual NLP
• A Thorough Examination of the CNN/Daily Mail Reading Comprehension Task
• Lambda Dependency-Based Compositional Semantics
• Language to Logical Form with Neural Attention
• Learning Dependency-Based Compositional Semantics
• Getting More Out Of Syntax with PropS
• Universal Semantic Parsing
• Learning Structured Natural Language Representations for Semantic Parsing
• Fast(er) Exact Decoding and Global Training for Transition-Based Dependency Parsing via a Minimal Feature Set
• Learning Cross-lingual Distributed Logical Representations for Semantic Parsing