mlsanityData to 7 Oct 2026

Compositional generalization through meta sequence-to-sequence learning

arXiv 1906.05381 ↗First posted 12 Jun 2019cs.CL cs.AI cs.LGcited by 98

Not on the map. Why?

Abstract (arXiv)

People can learn a new concept and use it compositionally, understanding how to "blicket twice" after learning how to "blicket." In contrast, powerful sequence-to-sequence (seq2seq) neural networks fail such tests of compositionality, especially when composing new concepts together with existing concepts. In this paper, I show how memory-augmented neural networks can be trained to generalize compositionally through meta seq2seq learning. In this approach, models train on a series of seq2seq problems to acquire the compositional skills needed to solve new seq2seq problems. Meta se2seq learning solves several of the SCAN tests for compositional learning and can learn to apply implicit rules to variables.

Key facts. Cited by 98 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 30; 2022: 32; 2023: 19; 2024: 8; 2025: 7; 2026: 2.

98 papers.

Sort:

By area:

  1. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  2. 2022Diverse Demonstrations Improve In-context Compositional Generalizationcited by 136
  3. 2021The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformerscited by 117
  4. 2022The CLRS Algorithmic Reasoning Benchmarkcited by 103
  5. 2022Compositional Semantic Parsing with Large Language Modelscited by 95
  6. 2021Survey of Low-Resource Machine Translationcited by 92
  7. 2021LTL2Action: Generalizing LTL Instructions for Multi-Task RLcited by 72
  8. 2021Meta-Learning to Compositionally Generalizecited by 62
  9. 2021The Neural Data Router: Adaptive Control Flow in Transformers Improves Systematic Generalizationcited by 62
  10. 2022Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learningcited by 59
  11. 2021The paradox of the compositionality of natural language: a neural machine translation case studycited by 58
  12. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
38 more
  1. 2022Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsingcited by 50
  2. 2021Improving Compositional Generalization with Latent Structure and Data Augmentationcited by 46
  3. 2023Break It Down: Evidence for Structural Compositionality in Neural Networkscited by 44
  4. 2023Modeling rapid language learning by distilling Bayesian priors into artificial neural networkscited by 40
  5. 2021Systematic Generalization with Edge Transformerscited by 38
  6. 2022SeqZero: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Modelscited by 38
  7. 2022The Neural Race Reduction: Dynamics of Abstraction in Gated Networkscited by 37
  8. 2021On Compositional Generalization of Neural Machine Translationcited by 34
  9. 2021Learning Algebraic Recombination for Compositional Generalizationcited by 31
  10. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  11. 2021Finding needles in a haystack: Sampling Structurally-diverse Training Sets from Synthetic Data for Compositional Generalizationcited by 27
  12. 2021Symbolic Brittleness in Sequence Models: on Systematic Generalization in Symbolic Mathematicscited by 27
  13. 2022How to Reuse and Compose Knowledge for a Lifetime of Tasks: A Survey on Continual Learning and Functional Compositioncited by 27
  14. 2023Neural-Logic Human-Object Interaction Detectioncited by 25
  15. 2021Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Taskscited by 24
  16. 2022On the Compositional Generalization Gap of In-Context Learningcited by 24
  17. 2022Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Modelscited by 22
  18. 2021Composing Partial Differential Equations with Physics-Aware Neural Networkscited by 21
  19. 2022Revisiting the Compositional Generalization Abilities of Neural Sequence Modelscited by 20
  20. 2021ReaSCAN: Compositional Reasoning in Language Groundingcited by 19
  21. 2021Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Taskscited by 19
  22. 2021Improving Compositional Generalization with Self-Training for Data-to-Text Generationcited by 19
  23. 2023Variational Cross-Graph Reasoning and Adaptive Structured Semantics Learning for Compositional Temporal Groundingcited by 19
  24. 2021In a Nutshell, the Human Asked for This: Latent Goals for Following Temporal Specificationscited by 17
  25. 2023ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesiscited by 17
  26. 2021Few-Shot Learning with a Strong Teachercited by 16
  27. 2022SUBS: Subtree Substitution for Compositional Semantic Parsingcited by 16
  28. 2021Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCANcited by 14
  29. 2022Improving Systematic Generalization Through Modularity and Augmentationcited by 13
  30. 2022Neural-Symbolic Recursive Machine for Systematic Generalizationcited by 12
  31. 2022When Can Transformers Ground and Compose: Insights from Compositional Generalization Benchmarkscited by 11
  32. 2023A Comprehensive Evaluation of Neural SPARQL Query Generation from Natural Language Questionscited by 9
  33. 2022Structurally Diverse Sampling for Sample-Efficient Training and Comprehensive Evaluationcited by 8
  34. 2022Mutual Exclusivity Training and Primitive Augmentation to Induce Compositionalitycited by 8
  35. 2023Learning to Substitute Spans towards Improving Compositional Generalizationcited by 8
  36. 2023MAGNIFICo: Evaluating the In-Context Learning Ability of Large Language Models to Generalize to Novel Interpretationscited by 7
  37. 2024From Frege to chatGPT: Compositionality in language, cognition, and deep neural networkscited by 7
  38. 2021A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semanticscited by 6

50 most cited of 98 All 98 (JSON)