{"url":"/task/constituency-grammar-induction","name":"Constituency Grammar Induction","slug":"constituency-grammar-induction","description_markdown":"Inducing a constituency-based phrase structure grammar.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":22,"papers_with_code":20,"benchmarks":4,"benchmark_tables_in_archive":5,"benchmark_tables_shown":5,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","slug":"constituency-grammar-induction-on-ptb","dataset":"PTB Diagnostic ECG Database","dataset_url":"/dataset/ptb","rows_in_archive":24,"metrics":["Mean F1 (WSJ)","Max F1 (WSJ)","Mean F1 (WSJ10)","Max F1 (WSJ10)"],"first_row_in_archive_order":{"model":"Ensemble (Generative MBR)","paper_title":"Ensemble Distillation for Unsupervised Constituency Parsing","paper_url":"/paper/ensemble-distillation-for-unsupervised","paper_date":"2023-10-03","arxiv_id":"2310.01717","code_links":[{"title":"manga-uofa/ed4ucp","url":"https://github.com/manga-uofa/ed4ucp"}],"syntology":{"n":22,"n_ran":16,"n_unverified":6,"n_pointer_only":22}}},{"leaderboard":"/sota/constituency-grammar-induction-on-ctb","slug":"constituency-grammar-induction-on-ctb","dataset":"CTB","dataset_url":null,"rows_in_archive":1,"metrics":["Mean F1"],"first_row_in_archive_order":{"model":"SemInfo-NPCFG (60NT)","paper_title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","paper_url":"/paper/improving-unsupervised-constituency-parsing","paper_date":"2024-10-03","arxiv_id":"2410.02558","code_links":[{"title":"junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information","url":"https://github.com/junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/constituency-grammar-induction-on-spmrl","slug":"constituency-grammar-induction-on-spmrl","dataset":"SPMRL French","dataset_url":null,"rows_in_archive":1,"metrics":["Mean F1"],"first_row_in_archive_order":{"model":"SemInfo-SNPCFG (1024NT)","paper_title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","paper_url":"/paper/improving-unsupervised-constituency-parsing","paper_date":"2024-10-03","arxiv_id":"2410.02558","code_links":[{"title":"junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information","url":"https://github.com/junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/constituency-grammar-induction-on-spmrl-1","slug":"constituency-grammar-induction-on-spmrl-1","dataset":"SPMRL German","dataset_url":null,"rows_in_archive":1,"metrics":["Mean F1"],"first_row_in_archive_order":{"model":"SemInfo-NPCFG (60NT)","paper_title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","paper_url":"/paper/improving-unsupervised-constituency-parsing","paper_date":"2024-10-03","arxiv_id":"2410.02558","code_links":[{"title":"junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information","url":"https://github.com/junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":null,"slug":"constituency-grammar-induction-on-penn","dataset":"Penn Treebank","dataset_url":"/dataset/penn-treebank","rows_in_archive":0,"metrics":["Mean F1 (WSJ)","Sentences F-Score"],"first_row_in_archive_order":null}],"datasets":[{"url":"/dataset/penn-treebank","name":"Penn Treebank","full_name":"","num_papers_in_archive":1006},{"url":"/dataset/ptb","name":"PTB Diagnostic ECG Database","full_name":"","num_papers_in_archive":22}],"subtasks":[],"parent_tasks":[{"url":"/task/constituency-parsing","name":"Constituency Parsing"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":20,"of":20,"tagged_in_all":22,"items":[{"url":"/paper/ordered-neurons-integrating-tree-structures","title":"Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks","date":"2018-10-22","arxiv_id":"1810.09536","repositories_listed":7,"syntology":{"n":12,"n_ran":3,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/generative-pretrained-structured-transformers","title":"Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale","date":"2024-03-13","arxiv_id":"2403.08293","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/dynamic-programming-in-rank-space-scaling-1","title":"Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs","date":"2022-05-01","arxiv_id":"2205.00484","repositories_listed":2,"syntology":null},{"url":"/paper/fast-r2d2-a-pretrained-recursive-neural","title":"Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation","date":"2022-03-01","arxiv_id":"2203.00281","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/compound-probabilistic-context-free-grammars","title":"Compound Probabilistic Context-Free Grammars for Grammar Induction","date":"2019-06-24","arxiv_id":"1906.10225","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/on-eliciting-syntax-from-language-models-via","title":"On Eliciting Syntax from Language Models via Hashing","date":"2024-10-05","arxiv_id":"2410.04074","repositories_listed":1,"syntology":null},{"url":"/paper/improving-unsupervised-constituency-parsing","title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","date":"2024-10-03","arxiv_id":"2410.02558","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/structural-optimization-ambiguity-and","title":"Structural Optimization Ambiguity and Simplicity Bias in Unsupervised Neural Grammar Induction","date":"2024-07-23","arxiv_id":"2407.16181","repositories_listed":1,"syntology":null},{"url":"/paper/simple-hardware-efficient-pcfgs-with","title":"Simple Hardware-Efficient PCFGs with Independent Left and Right Productions","date":"2023-10-23","arxiv_id":"2310.14997","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/ensemble-distillation-for-unsupervised","title":"Ensemble Distillation for Unsupervised Constituency Parsing","date":"2023-10-03","arxiv_id":"2310.01717","repositories_listed":1,"syntology":{"n":22,"n_ran":16,"n_unverified":6,"n_pointer_only":22}},{"url":"/paper/augmenting-transformers-with-recursively","title":"Augmenting Transformers with Recursively Composed Multi-grained Representations","date":"2023-09-28","arxiv_id":"2309.16319","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/co-training-an-unsupervised-constituency","title":"Co-training an Unsupervised Constituency Parser with Weak Supervision","date":"2021-10-05","arxiv_id":"2110.02283","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/dependency-induction-through-the-lens-of","title":"Dependency Induction Through the Lens of Visual Perception","date":"2021-09-20","arxiv_id":"2109.09790","repositories_listed":1,"syntology":null},{"url":"/paper/neural-bi-lexicalized-pcfg-induction","title":"Neural Bi-Lexicalized PCFG Induction","date":"2021-05-31","arxiv_id":"2105.15021","repositories_listed":1,"syntology":null},{"url":"/paper/pcfgs-can-do-better-inducing-probabilistic","title":"PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols","date":"2021-04-28","arxiv_id":"2104.13727","repositories_listed":1,"syntology":null},{"url":"/paper/visually-grounded-compound-pcfgs","title":"Visually Grounded Compound PCFGs","date":"2020-09-25","arxiv_id":"2009.12404","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-latent-tree-induction-with-deep-1","title":"Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders","date":"2019-06-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-recurrent-neural-network","title":"Unsupervised Recurrent Neural Network Grammars","date":"2019-04-07","arxiv_id":"1904.03746","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-learning-of-syntactic-structure","title":"Unsupervised Learning of Syntactic Structure with Invertible Neural Projections","date":"2018-08-28","arxiv_id":"1808.09111","repositories_listed":1,"syntology":null},{"url":"/paper/neural-language-modeling-by-jointly-learning","title":"Neural Language Modeling by Jointly Learning Syntax and Lexicon","date":"2017-11-02","arxiv_id":"1711.02013","repositories_listed":1,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}}],"syntology_records":10,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}