Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing
Ruisheng Cao Su Zhu Chenyu Yang Chen Liu Rao Ma Yanbin Zhao Lu Chen Kai Yu MoE Key Lab of Artificial Intelligence SpeechLab, Department of Computer Science and Engineering AI Institute, Shanghai Jiao Tong University, China The corresponding author is Kai Yu.
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.
中文速览
语义解析（semantic parsing）领域长期面临标注数据稀缺的难题，人工把自然语言转写成规范表达（canonical utterance）再配对逻辑形式既费时又易出错。为此，研究者提出了一个两阶段框架：第一阶段用一个无监督的改写模型（unsupervised paraphrase model）自动把自然语言句子转换成规范表达，第二阶段再用一个简单的神经语义解析器把规范表达映射到逻辑形式，从而把难题拆解为两个相对容易的子问题。训练过程分为预训练和循环学习两个阶段，引入了去噪自编码、回译和双重强化学习三类自监督任务，无需任何自然语言与规范表达之间的平行标注数据。在Overnight和GeoGranno两个基准上的实验表明，该方法在无监督设置下显著超越多个基线（包括需要人工标注的方法），在全监督设置下更分别以80.1%和74.5%的准确率刷新了当时的最优性能，为缓解语义解析中的数据稀缺问题提供了一条切实可行的路径。
原文 arXiv:2005.13485;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2005.13485v3