From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding

TL;DR

This paper introduces Synchronous Semantic Decoding (SSD), an unsupervised method that jointly addresses structural and semantic gaps in semantic parsing by leveraging paraphrasing and grammar constraints, achieving competitive results.

Contribution

The paper presents SSD, a novel unsupervised semantic parsing approach that jointly generates canonical utterances and logical forms through synchronized decoding.

Findings

SSD achieves competitive performance on multiple datasets.

The method effectively bridges semantic and structural gaps.

Synchronous decoding improves logical form generation accuracy.

Abstract

Semantic parsing is challenging due to the structure gap and the semantic gap between utterances and logical forms. In this paper, we propose an unsupervised semantic parsing method - Synchronous Semantic Decoding (SSD), which can simultaneously resolve the semantic gap and the structure gap by jointly leveraging paraphrasing and grammar constrained decoding. Specifically, we reformulate semantic parsing as a constrained paraphrasing problem: given an utterance, our model synchronously generates its canonical utterance and meaning representation. During synchronous decoding: the utterance paraphrasing is constrained by the structure of the logical form, therefore the canonical utterance can be paraphrased controlledly; the semantic decoding is guided by the semantics of the canonical utterance, therefore its logical form can be generated unsupervisedly. Experimental results show that SSD is a promising approach and can achieve competitive unsupervised semantic parsing performance on multiple datasets.