mlsanityData to 7 Oct 2026

Neural Bi-Lexicalized PCFG Induction

arXiv 2105.15021 ↗First posted 31 May 2021cs.CLcited by 18

Not on the map. Why?

Abstract (arXiv)

Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction. However, to reduce computational complexity, they make a strong independence assumption on the generation of the child word and thus bilexical dependencies are ignored. In this paper, we propose an approach to parameterize L-PCFGs without making implausible independence assumptions. Our approach directly models bilexical dependencies and meanwhile reduces both learning and representation complexities of L-PCFGs. Experimental results on the English WSJ dataset confirm the effectiveness of our approach in improving both running speed and unsupervised parsing performance.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 26 of its 57 references that are in the map. First posted on arXiv 31 May 2021.

Builds on

26 of 57 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019Compound Probabilistic Context-Free Grammars for Grammar Inductioncited by 76
  3. 2019Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoderscited by 60
  4. 2017Neural Language Modeling by Jointly Learning Syntax and Lexiconcited by 57
  5. 2020Fast and Accurate Neural CRF Constituency Parsingcited by 50
  6. 2019Visually Grounded Neural Syntax Acquisitioncited by 48
  7. 2020Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Inductioncited by 47
  8. 2020Torch-Struct: Deep Structured Prediction Librarycited by 40
  9. 2020Visually Grounded Compound PCFGscited by 34
  10. 2020StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modelingcited by 33
  11. 2020Unsupervised Parsing via Constituency Testscited by 23
  12. 2020Scaling Hidden Markov Language Modelscited by 22
14 more
  1. 2021PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbolscited by 22
  2. 2019Ordered Memorycited by 20
  3. 2020The Return of Lexical Dependencies: Neural Lexicalized PCFGscited by 19
  4. 2021Video-aided Unsupervised Grammar Inductioncited by 17
  5. 2020Heads-up! Unsupervised Constituency Parsing via Self-Attention Headscited by 12
  6. 2018Unsupervised Learning of Syntactic Structure with Invertible Neural Projectionscited by 11
  7. 2020Second-Order Unsupervised Neural Dependency Parsingcited by 10
  8. 2018Unsupervised Grammar Induction with Depth-bounded PCFGcited by 8
  9. 2017Dependency Grammar Induction with Neural Lexicalization and Big Training Datacited by 7
  10. 2020A Survey of Unsupervised Dependency Parsingcited by 6
  11. 2018Depth-bounding is effective: Improvements and evaluation of unsupervised PCFG inductioncited by 4
  12. 2021Learning Syntax from Naturally-Occurring Bracketingscited by 4
  13. 2021Rule Augmented Unsupervised Constituency Parsingcited by 4
  14. 2016Left-corner Methods for Syntactic Modeling with Universal Structural Constraintscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 7; 2023: 4; 2024: 3; 2025: 1; 2026: 1.

18 papers.

Sort:

  1. 2022Same Pre-training Loss, Better Downstream: Implicit Bias Matters for Language Modelscited by 84
  2. 2023Grammar Prompting for Domain-Specific Language Generation with Large Language Modelscited by 58
  3. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  4. 2021Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Argumentscited by 14
  5. 2022Nested Named Entity Recognition as Latent Lexicalized Constituency Parsingcited by 14
  6. 2022Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGscited by 10
  7. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  8. 2022Unsupervised Discontinuous Constituency Parsing with Mildly Context-Sensitive Grammarscited by 7
  9. 2023Augmenting Transformers with Recursively Composed Multi-grained Representationscited by 5
  10. 2022Learning a Grammar Inducer from Massive Uncurated Instructional Videoscited by 3
  11. 2023Simple Hardware-Efficient PCFGs with Independent Left and Right Productionscited by 3
  12. 2023Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentencescited by 2
6 more
  1. 2022Modeling Label Correlations for Second-Order Semantic Dependency Parsing with Mean-Field Inferencecited by 1
  2. 2024Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Inductioncited by 1
  3. 2024Improving Unsupervised Constituency Parsing via Maximizing Semantic Informationcited by 1
  4. 2024On Eliciting Syntax from Language Models via Hashingcited by 0
  5. 2025Probability Distribution Collapse: A Critical Bottleneck to Compact Unsupervised Neural Grammar Inductioncited by 0
  6. 2026Holographic Neural PCFG for Unsupervised Parsingcited by 0