# Compositional Networks Enable Systematic Generalization for Grounded Language Understanding

arXiv: https://arxiv.org/abs/2008.02742 · HTML: https://mlsanity.com/paper/2008.02742/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Aug 2020.

## Built on by (most cited first, 18 of 18)

- [Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modelling](https://mlsanity.com/paper/2301.12050/) (2023)
- [Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors](https://mlsanity.com/paper/2209.02485/) (2022)
- [Systematic Generalization on gSCAN: What is Nearly Solved and What is Next?](https://mlsanity.com/paper/2109.12243/) (2021)
- [A Survey on Compositional Learning of AI Models: Theoretical and Experimental Practices](https://mlsanity.com/paper/2406.08787/) (2024)
- [Improving Systematic Generalization Through Modularity and Augmentation](https://mlsanity.com/paper/2202.10745/) (2022)
- [Learning to Compose: Improving Object Centric Learning by Injecting Compositionality](https://mlsanity.com/paper/2405.00646/) (2024)
- [When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarks](https://mlsanity.com/paper/2210.12786/) (2022)
- [Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics](https://mlsanity.com/paper/2409.09626/) (2024)
- [Compositional Generalization in Grounded Language Learning via Induced Model Sparsity](https://mlsanity.com/paper/2207.02518/) (2022)
- [Recursive Decoding: A Situated Cognition Approach to Compositional Generation in Grounded Language Understanding](https://mlsanity.com/paper/2201.11766/) (2022)
- [Bag-of-Vectors Autoencoders for Unsupervised Conditional Text Generation](https://mlsanity.com/paper/2110.07002/) (2021)
- [Syntax-Guided Transformers: Elevating Compositional Generalization and Grounding in Multimodal Environments](https://mlsanity.com/paper/2311.04364/) (2023)
- [Compositional Generalization in Spoken Language Understanding](https://mlsanity.com/paper/2312.15815/) (2023)
- [Disentangled Representation Learning via Modular Compositional Bias](https://mlsanity.com/paper/2510.21402/) (2025)
- [A Short Survey of Systematic Generalization](https://mlsanity.com/paper/2211.11956/) (2022)
- [Data Distributional Properties As Inductive Bias for Systematic Generalization](https://mlsanity.com/paper/2502.20499/) (2025)
- [Independent Density Estimation](https://mlsanity.com/paper/2512.10067/) (2025)
- [What Do Current Systematic Generalization Tasks Miss? A Reasoning-Centered Analysis](https://mlsanity.com/paper/2609.19212/) (2026)

## Abstract (arXiv)

Humans are remarkably flexible when understanding new sentences that include combinations of concepts they have never encountered before. Recent work has shown that while deep networks can mimic some human language abilities when presented with novel sentences, systematic variation uncovers the limitations in the language-understanding abilities of networks. We demonstrate that these limitations can be overcome by addressing the generalization challenges in the gSCAN dataset, which explicitly measures how well an agent is able to interpret novel linguistic commands grounded in vision, e.g., novel pairings of adjectives and nouns. The key principle we employ is compositionality: that the compositional structure of networks should reflect the compositional structure of the problem domain they address, while allowing other parameters to be learned end-to-end. We build a general-purpose mechanism that enables agents to generalize their language understanding to compositional domains. Crucially, our network has the same state-of-the-art performance as prior work while generalizing its knowledge when prior work does not. Our network also provides a level of interpretability that enables users to inspect what each part of networks learns. Robust grounded language understanding without dramatic failures and without corner cases is critical to building safe and fair robots; we demonstrate the significant role that compositionality can play in achieving that goal.