# Cross-domain Semantic Parsing via Paraphrasing

arXiv: https://arxiv.org/abs/1704.05974 · HTML: https://mlsanity.com/paper/1704.05974/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2017.

## Built on by (most cited first, 19 of 19)

- [Improving Coherence and Consistency in Neural Sequence Models with Dual-System, Neuro-Symbolic Reasoning](https://mlsanity.com/paper/2107.02794/) (2021)
- [Controllable Semantic Parsing via Retrieval Augmentation](https://mlsanity.com/paper/2110.08458/) (2021)
- [Program Transfer for Answering Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2110.05743/) (2021)
- [ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation](https://mlsanity.com/paper/2101.08382/) (2021)
- [From Paraphrasing to Semantic Parsing: Unsupervised Semantic Parsing via Synchronous Semantic Decoding](https://mlsanity.com/paper/2106.06228/) (2021)
- [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)
- [Privacy-Preserving Domain Adaptation of Semantic Parsers](https://mlsanity.com/paper/2212.10520/) (2022)
- [Meta-Learning a Cross-lingual Manifold for Semantic Parsing](https://mlsanity.com/paper/2209.12577/) (2022)
- [Are Large Language Models Good Classifiers? A Study on Edit Intent Classification in Scientific Document Revisions](https://mlsanity.com/paper/2410.02028/) (2024)
- [Few-Shot Semantic Parsing for New Predicates](https://mlsanity.com/paper/2101.10708/) (2021)
- [Learning from Executions for Semantic Parsing](https://mlsanity.com/paper/2104.05819/) (2021)
- [Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing](https://mlsanity.com/paper/2210.01425/) (2022)
- [One Semantic Parser to Parse Them All: Sequence to Sequence Multi-Task Learning on Semantic Parsing Datasets](https://mlsanity.com/paper/2106.04476/) (2021)
- [Semantic-aware Contrastive Learning for More Accurate Semantic Parsing](https://mlsanity.com/paper/2301.07919/) (2023)
- [Improving Cause-of-Death Classification from Verbal Autopsy Reports](https://mlsanity.com/paper/2210.17161/) (2022)
- [What's Mine becomes Yours: Defining, Annotating and Detecting Context-Dependent Paraphrases in News Interview Dialogs](https://mlsanity.com/paper/2404.06670/) (2024)
- [Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering](https://mlsanity.com/paper/2410.00414/) (2024)
- [Automatic Translation of Hate Speech to Non-hate Speech in Social Media Texts](https://mlsanity.com/paper/2306.01261/) (2023)

## Abstract (arXiv)

Existing studies on semantic parsing mainly focus on the in-domain setting. We formulate cross-domain semantic parsing as a domain adaptation problem: train a semantic parser on some source domains and then adapt it to the target domain. Due to the diversity of logical forms in different domains, this problem presents unique and intriguing challenges. By converting logical forms into canonical utterances in natural language, we reduce semantic parsing to paraphrasing, and develop an attentive sequence-to-sequence paraphrase model that is general and flexible to adapt to different domains. We discover two problems, small micro variance and large macro variance, of pre-trained word embeddings that hinder their direct use in neural networks, and propose standardization techniques as a remedy. On the popular Overnight dataset, which contains eight domains, we show that both cross-domain training and standardized pre-trained word embeddings can bring significant improvement.