# Latent Compositional Representations Improve Systematic Generalization in Grounded Question Answering

arXiv: https://arxiv.org/abs/2007.00266 · HTML: https://mlsanity.com/paper/2007.00266/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2020.

## Built on by (most cited first, 16 of 16)

- [Towards Faithful Model Explanation in NLP: A Survey](https://mlsanity.com/paper/2209.11326/) (2022)
- [Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA](https://mlsanity.com/paper/2103.09591/) (2021)
- [Unobserved Local Structures Make Compositional Generalization Hard](https://mlsanity.com/paper/2201.05899/) (2022)
- [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)
- [Leveraging Code to Improve In-context Learning for Semantic Parsing](https://mlsanity.com/paper/2311.09519/) (2023)
- [Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluation](https://mlsanity.com/paper/2203.08445/) (2022)
- [Beam Tree Recursive Cells](https://mlsanity.com/paper/2305.19999/) (2023)
- [Efficient Beam Tree Recursion](https://mlsanity.com/paper/2307.10779/) (2023)
- [Learning with Latent Structures in Natural Language Processing: A Survey](https://mlsanity.com/paper/2201.00490/) (2022)
- [Semantic-aware Contrastive Learning for More Accurate Semantic Parsing](https://mlsanity.com/paper/2301.07919/) (2023)
- [Towards Equipping Transformer with the Ability of Systematic Compositionality](https://mlsanity.com/paper/2312.07280/) (2023)
- [Enhancing the Transformer Decoder with Transition-based Syntax](https://mlsanity.com/paper/2101.12640/) (2021)
- [Out-of-Distribution Generalization in Text Classification: Past, Present, and Future](https://mlsanity.com/paper/2305.14104/) (2023)
- [A Short Survey of Systematic Generalization](https://mlsanity.com/paper/2211.11956/) (2022)
- [Handling Open-Vocabulary Constructs in Formalizing Specifications: Retrieval-Augmented Parsing with Expert Knowledge](https://mlsanity.com/paper/2509.08808/) (2025)

## Abstract (arXiv)

Answering questions that involve multi-step reasoning requires decomposing them and using the answers of intermediate steps to reach the final answer. However, state-of-the-art models in grounded question answering often do not explicitly perform decomposition, leading to difficulties in generalization to out-of-distribution examples. In this work, we propose a model that computes a representation and denotation for all question spans in a bottom-up, compositional manner using a CKY-style parser. Our model induces latent trees, driven by end-to-end (the answer) supervision only. We show that this inductive bias towards tree structures dramatically improves systematic generalization to out-of-distribution examples, compared to strong baselines on an arithmetic expressions benchmark as well as on CLOSURE, a dataset that focuses on systematic generalization for grounded question answering. On this challenging dataset, our model reaches an accuracy of 96.1%, significantly higher than prior models that almost perfectly solve the task on a random, in-distribution split.