# Enforcing Consistency in Weakly Supervised Semantic Parsing

arXiv: https://arxiv.org/abs/2107.05833 · HTML: https://mlsanity.com/paper/2107.05833/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 17 references that are in the map.
- First posted on arXiv 13 Jul 2021.

## Builds on (most cited first, 3 of 3)

- [Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing](https://mlsanity.com/paper/1807.02322/) (2018)
- [From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood](https://mlsanity.com/paper/1704.07926/) (2017)
- [Weakly-supervised Semantic Parsing with Abstract Examples](https://mlsanity.com/paper/1711.05240/) (2017)

## Built on by (most cited first, 3 of 3)

- [lilGym: Natural Language Visual Reasoning with Reinforcement Learning](https://mlsanity.com/paper/2211.01994/) (2022)
- [Weakly Supervised Semantic Parsing with Execution-based Spurious Program Filtering](https://mlsanity.com/paper/2311.01161/) (2023)
- [Semantic Parsing with Candidate Expressions for Knowledge Base Question Answering](https://mlsanity.com/paper/2410.00414/) (2024)

## Abstract (arXiv)

The predominant challenge in weakly supervised semantic parsing is that of spurious programs that evaluate to correct answers for the wrong reasons. Prior work uses elaborate search strategies to mitigate the prevalence of spurious programs; however, they typically consider only one input at a time. In this work we explore the use of consistency between the output programs for related inputs to reduce the impact of spurious programs. We bias the program search (and thus the model's training signal) towards programs that map the same phrase in related inputs to the same sub-parts in their respective programs. Additionally, we study the importance of designing logical formalisms that facilitate this kind of consAistency-based training. We find that a more consistent formalism leads to improved model performance even without consistency-based training. When combined together, these two insights lead to a 10% absolute improvement over the best prior result on the Natural Language Visual Reasoning dataset.