mlsanityData to 7 Oct 2026

Hierarchical Poset Decoding for Compositional Generalization in Language

arXiv 2010.07792 ↗First posted 15 Oct 2020cs.CL cs.AIcited by 26

Not on the map. Why?

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.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Oct 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 3; 2023: 6; 2024: 3; 2025: 0; 2026: 2.

26 papers.

Sort:

  1. 2021The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformerscited by 117
  2. 2022Compositional Semantic Parsing with Large Language Modelscited by 95
  3. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  4. 2021Complex Knowledge Base Question Answering: A Surveycited by 52
  5. 2021Systematic Generalization with Edge Transformerscited by 38
  6. 2021Learning Algebraic Recombination for Compositional Generalizationcited by 31
  7. 2021Disentangled Sequence to Sequence Learning for Compositional Generalizationcited by 30
  8. 2021Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalizationcited by 27
  9. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  10. 2021SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoningcited by 10
  11. 2021Compositional Generalization in Multilingual Semantic Parsing over Wikidatacited by 9
  12. 2021LAGr: Labeling Aligned Graphs for Improving Systematic Generalization in Semantic Parsingcited by 7
14 more
  1. 2023SIP: Injecting a Structural Inductive Bias into a Seq2Seq Model by Simulationcited by 7
  2. 2021Grounded Graph Decoding Improves Compositional Generalization in Question Answeringcited by 6
  3. 2023On Evaluating Multilingual Compositional Generalization with Translated Datasetscited by 6
  4. 2024Towards Understanding the Relationship between In-context Learning and Compositional Generalizationcited by 5
  5. 2021Compositional Generalization in Dependency Parsingcited by 4
  6. 2023Learning to Compose Representations of Different Encoder Layers towards Improving Compositional Generalizationcited by 3
  7. 2024Sneaking Syntax into Transformer Language Models with Tree Regularizationcited by 3
  8. 2023Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsingcited by 2
  9. 2023Exploring the Compositional Generalization in Context Dependent Text-to-SQL Parsingcited by 2
  10. 2023Layer-wise Representation Fusion for Compositional Generalizationcited by 2
  11. 2026Reinforcement Learning for Compositional Generalization with Outcome-Level Optimizationcited by 1
  12. 2022LAGr: Label Aligned Graphs for Better Systematic Generalization in Semantic Parsingcited by 0
  13. 2024Machine Learning and Data Analysis Using Posets: A Surveycited by 0
  14. 2026Beyond Sequence Order: Syntax-Informed Positional Embeddings for Transformerscited by 0