# Grounded Graph Decoding Improves Compositional Generalization in Question Answering

arXiv: https://arxiv.org/abs/2111.03642 · HTML: https://mlsanity.com/paper/2111.03642/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 5 Nov 2021.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [Measuring Compositional Generalization: A Comprehensive Method on Realistic Data](https://mlsanity.com/paper/1912.09713/) (2019)
- [The Evolved Transformer](https://mlsanity.com/paper/1901.11117/) (2019)
- [Language to Logical Form with Neural Attention](https://mlsanity.com/paper/1601.01280/) (2016)
- [Improving Text-to-SQL Evaluation Methodology](https://mlsanity.com/paper/1806.09029/) (2018)
- [Case-based Reasoning for Natural Language Queries over Knowledge Bases](https://mlsanity.com/paper/2104.08762/) (2021)
- [Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures](https://mlsanity.com/paper/2007.08970/) (2020)
- [Compositional Questions Do Not Necessitate Multi-hop Reasoning](https://mlsanity.com/paper/1906.02900/) (2019)
- [Measuring Compositionality in Representation Learning](https://mlsanity.com/paper/1902.07181/) (2019)
- [Compositional Generalization via Neural-Symbolic Stack Machines](https://mlsanity.com/paper/2008.06662/) (2020)
- [Learning Compositional Rules via Neural Program Synthesis](https://mlsanity.com/paper/2003.05562/) (2020)
- [Compositional generalization in a deep seq2seq model by separating syntax and semantics](https://mlsanity.com/paper/1904.09708/) (2019)
- [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021)
- [AMR Parsing as Graph Prediction with Latent Alignment](https://mlsanity.com/paper/1805.05286/) (2018)
- [An Incremental Parser for Abstract Meaning Representation](https://mlsanity.com/paper/1608.06111/) (2016)
- [Lambda Dependency-Based Compositional Semantics](https://mlsanity.com/paper/1309.4408/) (2013)
- [Hierarchical Poset Decoding for Compositional Generalization in Language](https://mlsanity.com/paper/2010.07792/) (2020)
- [Robust Incremental Neural Semantic Graph Parsing](https://mlsanity.com/paper/1704.07092/) (2017)
- [Semantic Graph Parsing with Recurrent Neural Network DAG Grammars](https://mlsanity.com/paper/1910.00051/) (2019)

## Built on by (most cited first, 6 of 6)

- [State-of-the-art generalisation research in NLP: A taxonomy and review](https://mlsanity.com/paper/2210.03050/) (2022)
- [Compositional Semantic Parsing with Large Language Models](https://mlsanity.com/paper/2209.15003/) (2022)
- [A Survey on Compositional Generalization in Applications](https://mlsanity.com/paper/2302.01067/) (2023)
- [GenCHiP: Generating Robot Policy Code for High-Precision and Contact-Rich Manipulation Tasks](https://mlsanity.com/paper/2404.06645/) (2024)
- [Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing](https://mlsanity.com/paper/2305.04346/) (2023)
- [Bridging the gap to real-world language-grounded visual concept learning](https://mlsanity.com/paper/2510.21412/) (2025)

## Abstract (arXiv)

Question answering models struggle to generalize to novel compositions of training patterns, such to longer sequences or more complex test structures. Current end-to-end models learn a flat input embedding which can lose input syntax context. Prior approaches improve generalization by learning permutation invariant models, but these methods do not scale to more complex train-test splits. We propose Grounded Graph Decoding, a method to improve compositional generalization of language representations by grounding structured predictions with an attention mechanism. Grounding enables the model to retain syntax information from the input in thereby significantly improving generalization over complex inputs. By predicting a structured graph containing conjunctions of query clauses, we learn a group invariant representation without making assumptions on the target domain. Our model significantly outperforms state-of-the-art baselines on the Compositional Freebase Questions (CFQ) dataset, a challenging benchmark for compositional generalization in question answering. Moreover, we effectively solve the MCD1 split with 98% accuracy.