{"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/compound-probabilistic-context-free-grammars","title":"Compound Probabilistic Context-Free Grammars for Grammar Induction","arxiv_id":"1906.10225","date":"2019-06-24","proceeding":"ACL 2019 7","authors":["Yoon Kim","Chris Dyer","Alexander M. Rush"],"abstract":"We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our grammar's rule probabilities are modulated by a per-sentence continuous latent variable, which induces marginal dependencies beyond the traditional context-free assumptions. Inference in this grammar is performed by collapsed variational inference, in which an amortized variational posterior is placed on the continuous variable, and the latent trees are marginalized out with dynamic programming. Experiments on English and Chinese show the effectiveness of our approach compared to recent state-of-the-art methods when evaluated on unsupervised parsing.","url_abs":"https://arxiv.org/abs/1906.10225v9","url_pdf":"https://arxiv.org/pdf/1906.10225v9.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":"compound-probabilistic-context-free-grammars","repo_url":"https://github.com/harvardnlp/compound-pcfg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"compound-probabilistic-context-free-grammars","repo_url":"https://github.com/sustcsonglin/TN-PCFG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"constituency-grammar-induction","task_name":"Constituency Grammar Induction"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","task":"Constituency Grammar Induction","dataset":"PTB Diagnostic ECG Database","model":"Compound PCFG","rank_in_archive_order":15,"of":24,"metrics":{"Max F1 (WSJ)":"60.1","Max F1 (WSJ10)":"68.8","Mean F1 (WSJ)":"55.2"},"uses_additional_data":false},{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","task":"Constituency Grammar Induction","dataset":"PTB Diagnostic ECG Database","model":"Neural PCFG","rank_in_archive_order":17,"of":24,"metrics":{"Max F1 (WSJ)":"52.6","Mean F1 (WSJ)":"50.8"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.10225","atlas_url":"https://app.syntology.ai/?focus=1906.10225","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.10225"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/sustcsonglin/TN-PCFG","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/harvardnlp/compound-pcfg","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"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":"691b075efe15b91c","entry":"clean_number","repo":"harvardnlp/compound-pcfg","repo_kind":"official","path":"parse.py","file_url":"https://github.com/harvardnlp/compound-pcfg/blob/HEAD/parse.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"691b075efe15b91c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}