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

arXiv: https://arxiv.org/abs/2106.06228 · HTML: https://mlsanity.com/paper/2106.06228/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 61 references that are in the map.
- First posted on arXiv 11 Jun 2021.

## Builds on (most cited first, 27 of 27)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Data Recombination for Neural Semantic Parsing](https://mlsanity.com/paper/1606.03622/) (2016)
- [Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision](https://mlsanity.com/paper/1611.00020/) (2016)
- [Grounded Adaptation for Zero-shot Executable Semantic Parsing](https://mlsanity.com/paper/2009.07396/) (2020)
- [Learning to Paraphrase for Question Answering](https://mlsanity.com/paper/1708.06022/) (2017)
- [Decomposable Neural Paraphrase Generation](https://mlsanity.com/paper/1906.09741/) (2019)
- [Improving AMR Parsing with Sequence-to-Sequence Pre-training](https://mlsanity.com/paper/2010.01771/) (2020)
- [Question Generation from SQL Queries Improves Neural Semantic Parsing](https://mlsanity.com/paper/1808.06304/) (2018)
- [AutoQA: From Databases To QA Semantic Parsers With Only Synthetic Training Data](https://mlsanity.com/paper/2010.04806/) (2020)
- [Semantic Parsing with Dual Learning](https://mlsanity.com/paper/1907.05343/) (2019)
- [Don't paraphrase, detect! Rapid and Effective Data Collection for Semantic Parsing](https://mlsanity.com/paper/1908.09940/) (2019)
- [StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing](https://mlsanity.com/paper/1806.07832/) (2018)
- [Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing](https://mlsanity.com/paper/1809.00773/) (2018)
- [Unsupervised Dual Paraphrasing for Two-stage Semantic Parsing](https://mlsanity.com/paper/2005.13485/) (2020)
- [Cross-domain Semantic Parsing via Paraphrasing](https://mlsanity.com/paper/1704.05974/) (2017)
- [Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data](https://mlsanity.com/paper/2004.13645/) (2020)
- [Weakly-supervised Semantic Parsing with Abstract Examples](https://mlsanity.com/paper/1711.05240/) (2017)
- [Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing](https://mlsanity.com/paper/1804.07918/) (2018)
- [Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning](https://mlsanity.com/paper/1909.05438/) (2019)
- [Fast semantic parsing with well-typedness guarantees](https://mlsanity.com/paper/2009.07365/) (2020)
- [Inferring Logical Forms From Denotations](https://mlsanity.com/paper/1606.06900/) (2016)
- [Jointly Learning Semantic Parser and Natural Language Generator via Dual Information Maximization](https://mlsanity.com/paper/1906.00575/) (2019)
- [Look-up and Adapt: A One-shot Semantic Parser](https://mlsanity.com/paper/1910.12197/) (2019)
- [Unified Semantic Parsing with Weak Supervision](https://mlsanity.com/paper/1906.05062/) (2019)
- [Dependency-based Hybrid Trees for Semantic Parsing](https://mlsanity.com/paper/1809.00107/) (2018)

## Built on by (most cited first, 14 of 14)

- [Few-Shot Semantic Parsing with Language Models Trained On Code](https://mlsanity.com/paper/2112.08696/) (2021)
- [On the Evaluation Metrics for Paraphrase Generation](https://mlsanity.com/paper/2202.08479/) (2022)
- [On The Ingredients of an Effective Zero-shot Semantic Parser](https://mlsanity.com/paper/2110.08381/) (2021)
- [GraphQ IR: Unifying the Semantic Parsing of Graph Query Languages with One Intermediate Representation](https://mlsanity.com/paper/2205.12078/) (2022)
- [Generating Data for Symbolic Language with Large Language Models](https://mlsanity.com/paper/2305.13917/) (2023)
- [Addressing Resource and Privacy Constraints in Semantic Parsing Through Data Augmentation](https://mlsanity.com/paper/2205.08675/) (2022)
- [Training Naturalized Semantic Parsers with Very Little Data](https://mlsanity.com/paper/2204.14243/) (2022)
- [Semantic-aware Contrastive Learning for More Accurate Semantic Parsing](https://mlsanity.com/paper/2301.07919/) (2023)
- [Low-Resource Compositional Semantic Parsing with Concept Pretraining](https://mlsanity.com/paper/2301.09809/) (2023)
- [An In-Context Schema Understanding Method for Knowledge Base Question Answering](https://mlsanity.com/paper/2310.14174/) (2023)
- [Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering](https://mlsanity.com/paper/2410.00414/) (2024)
- [Action Controlled Paraphrasing](https://mlsanity.com/paper/2405.11277/) (2024)
- [SMCLM: Semantically Meaningful Causal Language Modeling for Autoregressive Paraphrase Generation](https://mlsanity.com/paper/2507.03415/) (2025)
- [GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement Learning](https://mlsanity.com/paper/2609.39869/) (2026)

## Abstract (arXiv)

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.