Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing

Abstract

One daunting problem for semantic parsing is the scarcity of annotation. Aiming to reduce nontrivial human labor, we propose a two-stage semantic parsing framework, where the first stage utilizes an unsupervised paraphrase model to convert an unlabeled natural language utterance into the canonical utterance. The downstream naive semantic parser accepts the intermediate output and returns the target logical form. Furthermore, the entire training process is split into two phases: pre-training and cycle learning. Three tailored self-supervised tasks are introduced throughout training to activate the unsupervised paraphrase model. Experimental results on benchmarks Overnight and GeoGranno demonstrate that our framework is effective and compatible with supervised training.

arXiv commentaccepted by ACL 2020 Long, 12 pages, 5 figures

References in corpus (7)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Convolutional Neural Networks for Sentence Classification
• Unsupervised Machine Translation Using Monolingual Corpora Only
• Unsupervised Neural Machine Translation
• A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer
• Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing