# Hierarchical Poset Decoding for Compositional Generalization in Language

arXiv: https://arxiv.org/abs/2010.07792 · HTML: https://mlsanity.com/paper/2010.07792/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Oct 2020.

## Built on by (most cited first, 26 of 26)

- [The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers](https://mlsanity.com/paper/2108.12284/) (2021)
- [Compositional Semantic Parsing with Large Language Models](https://mlsanity.com/paper/2209.15003/) (2022)
- [Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations](https://mlsanity.com/paper/2104.07478/) (2021)
- [Complex Knowledge Base Question Answering: A Survey](https://mlsanity.com/paper/2108.06688/) (2021)
- [Systematic Generalization with Edge Transformers](https://mlsanity.com/paper/2112.00578/) (2021)
- [Learning Algebraic Recombination for Compositional Generalization](https://mlsanity.com/paper/2107.06516/) (2021)
- [Disentangled Sequence to Sequence Learning for Compositional Generalization](https://mlsanity.com/paper/2110.04655/) (2021)
- [Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalization](https://mlsanity.com/paper/2109.02575/) (2021)
- [How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Composition](https://mlsanity.com/paper/2207.07730/) (2022)
- [SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning](https://mlsanity.com/paper/2110.14266/) (2021)
- [Compositional Generalization in Multilingual Semantic Parsing over Wikidata](https://mlsanity.com/paper/2108.03509/) (2021)
- [LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsing](https://mlsanity.com/paper/2110.07572/) (2021)
- [SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulation](https://mlsanity.com/paper/2310.00796/) (2023)
- [Grounded Graph Decoding Improves Compositional Generalization in Question Answering](https://mlsanity.com/paper/2111.03642/) (2021)
- [On Evaluating Multilingual Compositional Generalization with Translated Datasets](https://mlsanity.com/paper/2306.11420/) (2023)
- [Towards Understanding the Relationship between In-context Learning and Compositional Generalization](https://mlsanity.com/paper/2403.11834/) (2024)
- [Compositional Generalization in Dependency Parsing](https://mlsanity.com/paper/2110.06843/) (2021)
- [Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalization](https://mlsanity.com/paper/2305.12169/) (2023)
- [Sneaking Syntax into Transformer Language Models with Tree Regularization](https://mlsanity.com/paper/2411.18885/) (2024)
- [Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing](https://mlsanity.com/paper/2305.04346/) (2023)
- [Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsing](https://mlsanity.com/paper/2306.04480/) (2023)
- [Layer-wise Representation Fusion for Compositional Generalization](https://mlsanity.com/paper/2307.10799/) (2023)
- [Reinforcement Learning for Compositional Generalization with Outcome-Level Optimization](https://mlsanity.com/paper/2605.04920/) (2026)
- [LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsing](https://mlsanity.com/paper/2205.09607/) (2022)
- [Machine Learning and Data Analysis Using Posets: A Survey](https://mlsanity.com/paper/2404.03082/) (2024)
- [Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformers](https://mlsanity.com/paper/2608.06111/) (2026)

## Abstract (arXiv)

We formalize human language understanding as a structured prediction task where the output is a partially ordered set (poset). Current encoder-decoder architectures do not take the poset structure of semantics into account properly, thus suffering from poor compositional generalization ability. In this paper, we propose a novel hierarchical poset decoding paradigm for compositional generalization in language. Intuitively: (1) the proposed paradigm enforces partial permutation invariance in semantics, thus avoiding overfitting to bias ordering information; (2) the hierarchical mechanism allows to capture high-level structures of posets. We evaluate our proposed decoder on Compositional Freebase Questions (CFQ), a large and realistic natural language question answering dataset that is specifically designed to measure compositional generalization. Results show that it outperforms current decoders.