mlsanityData to 7 Oct 2026

Compound Probabilistic Context-Free Grammars for Grammar Induction

arXiv 1906.10225 ↗First posted 24 Jun 2019cs.CL stat.MLcited by 76

Not on the map. Why?

Abstract (arXiv)

We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our grammar's rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this grammar is performed by collapsed variational inference, in which an amortized variational posterior is placed on the continuous variable, and the latent trees are marginalized out with dynamic programming. Experiments on English and Chinese show the effectiveness of our approach compared to recent state-of-the-art methods when evaluated on unsupervised parsing.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 20; 2022: 16; 2023: 22; 2024: 14; 2025: 2; 2026: 2.

76 papers.

Sort:

By area:

  1. 2023A Theory of Emergent In-Context Learning as Implicit Structure Inductioncited by 86
  2. 2022Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Modelscited by 84
  3. 2023Uncertainty in Natural Language Generation: From Theory to Applicationscited by 61
  4. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  5. 2021Leveraging Language to Learn Program Abstractions and Search Heuristicscited by 44
  6. 2023HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attentioncited by 44
  7. 2023LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Modelcited by 43
  8. 2023GFlowNet-EM for learning compositional latent variable modelscited by 40
  9. 2023ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddingscited by 32
  10. 2021Learning Algebraic Recombination for Compositional Generalizationcited by 31
  11. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  12. 2021VLGrammar: Grounded Grammar Induction of Vision and Languagecited by 22
38 more
  1. 2021PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbolscited by 22
  2. 2021R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modelingcited by 19
  3. 2022How can NLP Help Revitalize Endangered Languages? A Case Study and Roadmap for the Cherokee Languagecited by 19
  4. 2021Neural Bi-Lexicalized PCFG Inductioncited by 18
  5. 2021Video-aided Unsupervised Grammar Inductioncited by 17
  6. 2021Learning Hierarchical Structures with Differentiable Nondeterministic Stackscited by 16
  7. 2022Finding Dataset Shortcuts with Grammar Inductioncited by 15
  8. 2022Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representationcited by 14
  9. 2024Analyzing The Language of Visual Tokenscited by 12
  10. 2022Unsupervised Slot Schema Induction for Task-oriented Dialogcited by 11
  11. 2022Grammar-Based Grounded Lexicon Learningcited by 10
  12. 2022Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGscited by 10
  13. 2022Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationshipscited by 9
  14. 2024Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scalecited by 9
  15. 2022Low-Rank Constraints for Fast Inference in Structured Modelscited by 8
  16. 2023Activity Grammars for Temporal Action Segmentationcited by 8
  17. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  18. 2022Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammarscited by 7
  19. 2023Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parserscited by 7
  20. 2021An Empirical Study of Compound PCFGscited by 6
  21. 2021Improved Latent Tree Induction with Distant Supervision via Span Constraintscited by 6
  22. 2023Ensemble Distillation for Unsupervised Constituency Parsingcited by 6
  23. 2021The Limitations of Limited Context for Constituency Parsingcited by 5
  24. 2023Augmenting Transformers with Recursively Composed Multi-grained Representationscited by 5
  25. 2024Compositional Generalization Across Distributional Shifts with Sparse Tree Operationscited by 5
  26. 2021Learning Syntax from Naturally-Occurring Bracketingscited by 4
  27. 2021Rule Augmented Unsupervised Constituency Parsingcited by 4
  28. 2022Syntactic Substitutability as Unsupervised Dependency Syntaxcited by 4
  29. 2024Graph Parsing Networkscited by 4
  30. 2024Finding structure in logographic writing with library learningcited by 4
  31. 2021Cetacean Translation Initiative: a roadmap to deciphering the communication of sperm whalescited by 3
  32. 2021Co-training an Unsupervised Constituency Parser with Weak Supervisioncited by 3
  33. 2021Recursive Bayesian Networks: Generalising and Unifying Probabilistic Context-Free Grammars and Dynamic Bayesian Networkscited by 3
  34. 2022Learning a Grammar Inducer from Massive Uncurated Instructional Videoscited by 3
  35. 2023Structured Generative Models for Scene Understandingcited by 3
  36. 2023Simple Hardware-Efficient PCFGs with Independent Left and Right Productionscited by 3
  37. 2024Tree Transformers are an Ineffective Model of Syntactic Constituencycited by 3
  38. 2021Dependency Induction Through the Lens of Visual Perceptioncited by 2

50 most cited of 76 All 76 (JSON)