# Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

arXiv: https://arxiv.org/abs/1804.07918 · HTML: https://mlsanity.com/paper/1804.07918/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2018.

## Built on by (most cited first, 11 of 11)

- [Word Alignment by Fine-tuning Embeddings on Parallel Corpora](https://mlsanity.com/paper/2101.08231/) (2021)
- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021)
- [MultiSpider: Towards Benchmarking Multilingual Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2212.13492/) (2022)
- [Zero-Shot Cross-lingual Semantic Parsing](https://mlsanity.com/paper/2104.07554/) (2021)
- [From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding](https://mlsanity.com/paper/2106.06228/) (2021)
- [Leveraging Code to Improve In-context Learning for Semantic Parsing](https://mlsanity.com/paper/2311.09519/) (2023)
- [Few-Shot Semantic Parsing for New Predicates](https://mlsanity.com/paper/2101.10708/) (2021)
- [Code Generation for Unknown Libraries via Reading API Documentations](https://mlsanity.com/paper/2202.07806/) (2022)
- [Low-Resource Compositional Semantic Parsing with Concept Pretraining](https://mlsanity.com/paper/2301.09809/) (2023)
- [Third-Party Aligner for Neural Word Alignments](https://mlsanity.com/paper/2211.04198/) (2022)

## Abstract (arXiv)

Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize to new domains. In this paper, we introduce a zero-shot approach to semantic parsing that can parse utterances in unseen domains while only being trained on examples in other source domains. First, we map an utterance to an abstract, domain-independent, logical form that represents the structure of the logical form, but contains slots instead of KB constants. Then, we replace slots with KB constants via lexical alignment scores and global inference. Our model reaches an average accuracy of 53.4% on 7 domains in the Overnight dataset, substantially better than other zero-shot baselines, and performs as good as a parser trained on over 30% of the target domain examples.