mlsanityData to 7 Oct 2026

Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders

arXiv 1904.02142 ↗First posted 3 Apr 2019cs.CLcited by 60

Not on the map. Why?

Abstract (arXiv)

We introduce deep inside-outside recursive autoencoders (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Our approach predicts each word in an input sentence conditioned on the rest of the sentence and uses inside-outside dynamic programming to consider all possible binary trees over the sentence. At test time the CKY algorithm extracts the highest scoring parse. DIORA achieves a new state-of-the-art F1 in unsupervised binary constituency parsing (unlabeled) in two benchmark datasets, WSJ and MultiNLI.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Apr 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 9; 2023: 21; 2024: 11; 2025: 2; 2026: 1.

60 papers.

Sort:

By area:

  1. 2023LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Modelcited by 43
  2. 2021VLGrammar: Grounded Grammar Induction of Vision and Languagecited by 22
  3. 2021PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbolscited by 22
  4. 2021R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modelingcited by 19
  5. 2021Interpreting Deep Learning Models in Natural Language Processing: A Reviewcited by 19
  6. 2021Neural Bi-Lexicalized PCFG Inductioncited by 18
  7. 2023Pushdown Layers: Encoding Recursive Structure in Transformer Language Modelscited by 18
  8. 2021Video-aided Unsupervised Grammar Inductioncited by 17
  9. 2021Modeling Hierarchical Structures with Continuous Recursive Neural Networkscited by 15
  10. 2022Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representationcited by 14
  11. 2022Grammar-Based Grounded Lexicon Learningcited by 10
  12. 2022Unsupervised Vision-Language Parsing: Seamlessly Bridging Visual Scene Graphs with Language Structures via Dependency Relationshipscited by 9
38 more
  1. 2024Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scalecited by 9
  2. 2023Contextual Distortion Reveals Constituency: Masked Language Models are Implicit Parserscited by 7
  3. 2021Improved Latent Tree Induction with Distant Supervision via Span Constraintscited by 6
  4. 2023Beam Tree Recursive Cellscited by 6
  5. 2023Ensemble Distillation for Unsupervised Constituency Parsingcited by 6
  6. 2023Augmenting Transformers with Recursively Composed Multi-grained Representationscited by 5
  7. 2023Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalabilitycited by 5
  8. 2021Learning Syntax from Naturally-Occurring Bracketingscited by 4
  9. 2021Rule Augmented Unsupervised Constituency Parsingcited by 4
  10. 2023A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classificationcited by 4
  11. 2023Efficient Beam Tree Recursioncited by 4
  12. 2024Graph Parsing Networkscited by 4
  13. 2021DeepCPCFG: Deep Learning and Context Free Grammars for End-to-End Information Extractioncited by 3
  14. 2022Forming Trees with Treeformerscited by 3
  15. 2022Learning a Grammar Inducer from Massive Uncurated Instructional Videoscited by 3
  16. 2023Efficient Semiring-Weighted Earley Parsingcited by 3
  17. 2023Weakly Supervised Reasoning by Neuro-Symbolic Approachescited by 3
  18. 2023ChapGTP, ILLC's Attempt at Raising a BabyLM: Improving Data Efficiency by Automatic Task Formationcited by 3
  19. 2023Enhancing Group Fairness in Online Settings Using Oblique Decision Forestscited by 3
  20. 2024Punctuation Restoration Improves Structure Understanding Without Supervisioncited by 3
  21. 2024Self-StrAE at SemEval-2024 Task 1: Making Self-Structuring AutoEncoders Learn More With Lesscited by 3
  22. 2024Banyan: Improved Representation Learning with Explicit Structurecited by 3
  23. 2022Learning with Latent Structures in Natural Language Processing: A Surveycited by 2
  24. 2022Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Inductioncited by 2
  25. 2023Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentencescited by 2
  26. 2023StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structurecited by 2
  27. 2023The Emergence of Chunking Structures with Hierarchical RNNcited by 2
  28. 2023Audio-Visual Neural Syntax Acquisitioncited by 2
  29. 2024Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction modelscited by 2
  30. 2021Unsupervised Learning of Explainable Parse Trees for Improved Generalisationcited by 1
  31. 2021Neural Sequence Segmentation as Determining the Leftmost Segmentscited by 1
  32. 2021ORCHARD: A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoningcited by 1
  33. 2023ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Timecited by 1
  34. 2023AMR Parsing with Causal Hierarchical Attention and Pointerscited by 1
  35. 2024Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Inductioncited by 1
  36. 2021Unsupervised Full Constituency Parsing with Neighboring Distribution Divergencecited by 0
  37. 2021FastTrees: Parallel Latent Tree-Induction for Faster Sequence Encodingcited by 0
  38. 2022Syntactic Inductive Biases for Deep Learning Methodscited by 0

50 most cited of 60 All 60 (JSON)