{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/co-training-an-unsupervised-constituency","title":"Co-training an Unsupervised Constituency Parser with Weak Supervision","arxiv_id":"2110.02283","date":"2021-10-05","proceeding":"Findings (ACL) 2022 5","authors":["Nickil Maveli","Shay B. Cohen"],"abstract":"We introduce a method for unsupervised parsing that relies on bootstrapping classifiers to identify if a node dominates a specific span in a sentence. There are two types of classifiers, an inside classifier that acts on a span, and an outside classifier that acts on everything outside of a given span. Through self-training and co-training with the two classifiers, we show that the interplay between them helps improve the accuracy of both, and as a result, effectively parse. A seed bootstrapping technique prepares the data to train these classifiers. Our analyses further validate that such an approach in conjunction with weak supervision using prior branching knowledge of a known language (left/right-branching) and minimal heuristics injects strong inductive bias into the parser, achieving 63.1 F$_1$ on the English (PTB) test set. In addition, we show the effectiveness of our architecture by evaluating on treebanks for Chinese (CTB) and Japanese (KTB) and achieve new state-of-the-art results. Our code and pre-trained models are available at https://github.com/Nickil21/weakly-supervised-parsing.","url_abs":"https://arxiv.org/abs/2110.02283v2","url_pdf":"https://arxiv.org/pdf/2110.02283v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"co-training-an-unsupervised-constituency","repo_url":"https://github.com/Nickil21/weakly-supervised-parsing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"constituency-grammar-induction","task_name":"Constituency Grammar Induction"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","task":"Constituency Grammar Induction","dataset":"PTB Diagnostic ECG Database","model":"inside-outside co-training + weak supervision","rank_in_archive_order":8,"of":24,"metrics":{"Max F1 (WSJ)":"66.8","Mean F1 (WSJ)":"63.1","Mean F1 (WSJ10)":"74.2"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.02283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.02283"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Nickil21/weakly-supervised-parsing","reach":null}],"summary":{"ran_honours":1,"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"d4b3f50524ef7245","entry":"get_stats","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"d4b3f50524ef7245"}},{"code_sha256_prefix":"625f98c10e41a690","entry":"is_next_open_bracket","repo":"Nickil21/weakly-supervised-parsing","repo_kind":"official","path":"weakly_supervised_parser/tree/compare_trees.py","file_url":"https://github.com/Nickil21/weakly-supervised-parsing/blob/HEAD/weakly_supervised_parser/tree/compare_trees.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"625f98c10e41a690"}},{"code_sha256_prefix":"73b59f573db79fdd","entry":"get_nonbinary_spans","repo":"Nickil21/weakly-supervised-parsing","repo_kind":"official","path":"weakly_supervised_parser/tree/compare_trees.py","file_url":"https://github.com/Nickil21/weakly-supervised-parsing/blob/HEAD/weakly_supervised_parser/tree/compare_trees.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"73b59f573db79fdd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}