# Neural Semantic Parsing over Multiple Knowledge-bases

arXiv: https://arxiv.org/abs/1702.01569 · HTML: https://mlsanity.com/paper/1702.01569/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2017.

## Built on by (most cited first, 8 of 8)

- [Program Transfer for Answering Complex Questions over Knowledge Bases](https://mlsanity.com/paper/2110.05743/) (2021)
- [Meta-Learning a Cross-lingual Manifold for Semantic Parsing](https://mlsanity.com/paper/2209.12577/) (2022)
- [Generate, Transform, Answer: Question Specific Tool Synthesis for Tabular Data](https://mlsanity.com/paper/2303.10138/) (2023)
- [Compositional Generalization in Multilingual Semantic Parsing over Wikidata](https://mlsanity.com/paper/2108.03509/) (2021)
- [Learning from Executions for Semantic Parsing](https://mlsanity.com/paper/2104.05819/) (2021)
- [SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts](https://mlsanity.com/paper/2110.01295/) (2021)
- [Structure-Augmented Reasoning Generation](https://mlsanity.com/paper/2506.08364/) (2025)
- [Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering](https://mlsanity.com/paper/2410.00414/) (2024)

## Abstract (arXiv)

A fundamental challenge in developing semantic parsers is the paucity of strong supervision in the form of language utterances annotated with logical form. In this paper, we propose to exploit structural regularities in language in different domains, and train semantic parsers over multiple knowledge-bases (KBs), while sharing information across datasets. We find that we can substantially improve parsing accuracy by training a single sequence-to-sequence model over multiple KBs, when providing an encoding of the domain at decoding time. Our model achieves state-of-the-art performance on the Overnight dataset (containing eight domains), improves performance over a single KB baseline from 75.6% to 79.6%, while obtaining a 7x reduction in the number of model parameters.