Semantic Parsing with Dual Learning
arXiv:1907.05343
Abstract
Semantic parsing converts natural language queries into structured logical forms. The paucity of annotated training samples is a fundamental challenge in this field. In this work, we develop a semantic parsing framework with the dual learning algorithm, which enables a semantic parser to make full use of data (labeled and even unlabeled) through a dual-learning game. This game between a primal model (semantic parsing) and a dual model (logical form to query) forces them to regularize each other, and can achieve feedback signals from some prior-knowledge. By utilizing the prior-knowledge of logical form structures, we propose a novel reward signal at the surface and semantic levels which tends to generate complete and reasonable logical forms. Experimental results show that our approach achieves new state-of-the-art performance on ATIS dataset and gets competitive performance on Overnight dataset.
Accepted by ACL 2019 Long Paper
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Sequence to Sequence Learning with Neural Networks
- Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
- NLTK: The Natural Language Toolkit
- Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
- Dual Learning for Machine Translation
- Question Answering and Question Generation as Dual Tasks
- Pointing the Unknown Words
- Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing
- AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning