{"url":"/task/constituency-parsing","name":"Constituency Parsing","slug":"constituency-parsing","description_markdown":"Constituency parsing aims to extract a constituency-based parse tree from a sentence that\r\nrepresents its syntactic structure according to a [phrase structure grammar](https://en.wikipedia.org/wiki/Phrase_structure_grammar).\r\n\r\nExample:\r\n\r\n                 Sentence (S)\r\n                     |\r\n       +-------------+------------+\r\n       |                          |\r\n     Noun (N)                Verb Phrase (VP)\r\n       |                          |\r\n     John                 +-------+--------+\r\n                          |                |\r\n                        Verb (V)         Noun (N)\r\n                          |                |\r\n                        sees              Bill\r\n\r\n[Recent approaches](https://papers.nips.cc/paper/5635-grammar-as-a-foreign-language.pdf)\r\nconvert the parse tree into a sequence following a depth-first traversal in order to\r\nbe able to apply sequence-to-sequence models to it. The linearized version of the\r\nabove parse tree looks as follows: (S (N) (VP V N)).","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":204,"papers_with_code":81,"benchmarks":4,"benchmark_tables_in_archive":4,"benchmark_tables_shown":4,"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":6,"subtasks":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/constituency-parsing-on-penn-treebank","slug":"constituency-parsing-on-penn-treebank","dataset":"Penn Treebank","dataset_url":"/dataset/penn-treebank","rows_in_archive":27,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"Hashing + XLNet","paper_title":"To be Continuous, or to be Discrete, Those are Bits of Questions","paper_url":"/paper/to-be-continuous-or-to-be-discrete-those-are","paper_date":"2024-06-12","arxiv_id":"2406.07812","code_links":[{"title":"speedcell4/parserker","url":"https://github.com/speedcell4/parserker"}],"syntology":null}},{"leaderboard":"/sota/constituency-parsing-on-ctb5","slug":"constituency-parsing-on-ctb5","dataset":"CTB5","dataset_url":null,"rows_in_archive":9,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"Attach-Juxtapose Parser + BERT","paper_title":"Strongly Incremental Constituency Parsing with Graph Neural Networks","paper_url":"/paper/strongly-incremental-constituency-parsing","paper_date":"2020-10-27","arxiv_id":"2010.14568","code_links":[{"title":"yzhangcs/parser","url":"https://github.com/yzhangcs/parser"},{"title":"princeton-vl/attach-juxtapose-parser","url":"https://github.com/princeton-vl/attach-juxtapose-parser"},{"title":"anaezquerro/incpar","url":"https://github.com/anaezquerro/incpar"}],"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}}},{"leaderboard":"/sota/constituency-parsing-on-ctb7","slug":"constituency-parsing-on-ctb7","dataset":"CTB7","dataset_url":null,"rows_in_archive":3,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"CRF Parser + Electra","paper_title":"Fast and Accurate Neural CRF Constituency Parsing","paper_url":"/paper/fast-and-accurate-neural-crf-constituency-1","paper_date":"2020-08-09","arxiv_id":"2008.03736","code_links":[{"title":"yzhangcs/parser","url":"https://github.com/yzhangcs/parser"},{"title":"yzhangcs/crfpar","url":"https://github.com/yzhangcs/crfpar"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/constituency-parsing-on-atb","slug":"constituency-parsing-on-atb","dataset":"ATB","dataset_url":null,"rows_in_archive":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"SAPar","paper_title":"Improving Constituency Parsing with Span Attention","paper_url":"/paper/improving-constituency-parsing-with-span","paper_date":"2020-10-15","arxiv_id":"2010.07543","code_links":[{"title":"cuhksz-nlp/SAPar","url":"https://github.com/cuhksz-nlp/SAPar"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/penn-treebank","name":"Penn Treebank","full_name":"","num_papers_in_archive":1006},{"url":"/dataset/flue-french-language-understanding-evaluation","name":"FLUE","full_name":"French Language Understanding Evaluation","num_papers_in_archive":12},{"url":"/dataset/taiga-corpus","name":"Taiga Corpus","full_name":"An open-source corpus for machine learning.","num_papers_in_archive":5},{"url":"/dataset/pcc","name":"PCC","full_name":"Potsdam Commentary Corpus","num_papers_in_archive":2},{"url":"/dataset/alexa-point-of-view","name":"Alexa Point of View","full_name":null,"num_papers_in_archive":1},{"url":"/dataset/masc","name":"MASC","full_name":"Manually Annotated Sub-Corpus","num_papers_in_archive":1}],"subtasks":[{"url":"/task/constituency-grammar-induction","name":"Constituency Grammar Induction"}],"parent_tasks":[],"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":30,"of":81,"tagged_in_all":204,"items":[{"url":"/paper/scheduled-sampling-for-sequence-prediction","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","date":"2015-06-09","arxiv_id":"1506.03099","repositories_listed":9,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/grammar-as-a-foreign-language","title":"Grammar as a Foreign Language","date":"2014-12-23","arxiv_id":"1412.7449","repositories_listed":7,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/recurrent-neural-network-grammars","title":"Recurrent Neural Network Grammars","date":"2016-02-25","arxiv_id":"1602.07776","repositories_listed":6,"syntology":{"n":10,"n_ran":6,"n_unverified":4,"n_pointer_only":6}},{"url":"/paper/constituency-parsing-with-a-self-attentive","title":"Constituency Parsing with a Self-Attentive Encoder","date":"2018-05-02","arxiv_id":"1805.01052","repositories_listed":5,"syntology":{"n":14,"n_ran":0,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/multilingual-constituency-parsing-with-self","title":"Multilingual Constituency Parsing with Self-Attention and Pre-Training","date":"2018-12-31","arxiv_id":"1812.11760","repositories_listed":4,"syntology":{"n":28,"n_ran":3,"n_unverified":25,"n_pointer_only":3}},{"url":"/paper/strongly-incremental-constituency-parsing","title":"Strongly Incremental Constituency Parsing with Graph Neural Networks","date":"2020-10-27","arxiv_id":"2010.14568","repositories_listed":3,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/generalizing-natural-language-analysis-1","title":"Generalizing Natural Language Analysis through Span-relation Representations","date":"2019-11-10","arxiv_id":"1911.03822","repositories_listed":3,"syntology":null},{"url":"/paper/unsupervised-latent-tree-induction-with-deep","title":"Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders","date":"2019-04-03","arxiv_id":"1904.02142","repositories_listed":3,"syntology":{"n":16,"n_ran":4,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/flexible-grammar-based-constrained-decoding","title":"Grammar-Constrained Decoding for Structured NLP Tasks without Finetuning","date":"2023-05-23","arxiv_id":"2305.13971","repositories_listed":2,"syntology":{"n":14,"n_ran":2,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/challenges-to-open-domain-constituency","title":"Challenges to Open-Domain Constituency Parsing","date":"2022-05-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/structformer-joint-unsupervised-induction-of-1","title":"StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling","date":"2020-12-01","arxiv_id":"2012.00857","repositories_listed":2,"syntology":null},{"url":"/paper/converting-the-point-of-view-of-messages","title":"Converting the Point of View of Messages Spoken to Virtual Assistants","date":"2020-10-06","arxiv_id":"2010.02600","repositories_listed":2,"syntology":null},{"url":"/paper/fast-and-accurate-neural-crf-constituency-1","title":"Fast and Accurate Neural CRF Constituency Parsing","date":"2020-08-09","arxiv_id":"2008.03736","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/rethinking-self-attention-an-interpretable","title":"Rethinking Self-Attention: Towards Interpretability in Neural Parsing","date":"2019-11-10","arxiv_id":"1911.03875","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/tetra-tagging-word-synchronous-parsing-with","title":"Tetra-Tagging: Word-Synchronous Parsing with Linear-Time Inference","date":"2019-04-22","arxiv_id":"1904.09745","repositories_listed":2,"syntology":null},{"url":"/paper/straight-to-the-tree-constituency-parsing","title":"Straight to the Tree: Constituency Parsing with Neural Syntactic Distance","date":"2018-06-11","arxiv_id":"1806.04168","repositories_listed":2,"syntology":null},{"url":"/paper/yellowfin-and-the-art-of-momentum-tuning","title":"YellowFin and the Art of Momentum Tuning","date":"2017-06-12","arxiv_id":"1706.03471","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/automatic-extraction-of-clausal-embedding","title":"Automatic Extraction of Clausal Embedding Based on Large-Scale English Text Data","date":"2025-06-16","arxiv_id":"2506.14064","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/to-be-continuous-or-to-be-discrete-those-are","title":"To be Continuous, or to be Discrete, Those are Bits of Questions","date":"2024-06-12","arxiv_id":"2406.07812","repositories_listed":1,"syntology":null},{"url":"/paper/ensemble-based-unsupervised-discontinuous","title":"Tree-Averaging Algorithms for Ensemble-Based Unsupervised Discontinuous Constituency Parsing","date":"2024-02-29","arxiv_id":"2403.00143","repositories_listed":1,"syntology":{"n":10,"n_ran":8,"n_unverified":2,"n_pointer_only":10}},{"url":"/paper/structured-tree-alignment-for-evaluation-of","title":"Structured Tree Alignment for Evaluation of (Speech) Constituency Parsing","date":"2024-02-21","arxiv_id":"2402.13433","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/sketch-guided-constrained-decoding-for","title":"Sketch-Guided Constrained Decoding for Boosting Blackbox Large Language Models without Logit Access","date":"2024-01-18","arxiv_id":"2401.09967","repositories_listed":1,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":7}},{"url":"/paper/multistage-collaborative-knowledge","title":"Multistage Collaborative Knowledge Distillation from a Large Language Model for Semi-Supervised Sequence Generation","date":"2023-11-15","arxiv_id":"2311.08640","repositories_listed":1,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/llm-enhanced-self-training-for-cross-domain","title":"LLM-enhanced Self-training for Cross-domain Constituency Parsing","date":"2023-11-05","arxiv_id":"2311.02660","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/depnecti-dependency-based-nested-compound","title":"DepNeCTI: Dependency-based Nested Compound Type Identification for Sanskrit","date":"2023-10-14","arxiv_id":"2310.09501","repositories_listed":1,"syntology":null},{"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/approximating-cky-with-transformers","title":"Approximating CKY with Transformers","date":"2023-05-03","arxiv_id":"2305.02386","repositories_listed":1,"syntology":null}],"syntology_records":18,"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"}}