{"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/improving-unsupervised-constituency-parsing","title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","arxiv_id":"2410.02558","date":"2024-10-03","proceeding":null,"authors":["Junjie Chen","Xiangheng He","Yusuke Miyao","Danushka Bollegala"],"abstract":"Unsupervised constituency parsers organize phrases within a sentence into a tree-shaped syntactic constituent structure that reflects the organization of sentence semantics. However, the traditional objective of maximizing sentence log-likelihood (LL) does not explicitly account for the close relationship between the constituent structure and the semantics, resulting in a weak correlation between LL values and parsing accuracy. In this paper, we introduce a novel objective for training unsupervised parsers: maximizing the information between constituent structures and sentence semantics (SemInfo). We introduce a bag-of-substrings model to represent the semantics and apply the probability-weighted information metric to estimate the SemInfo. Additionally, we develop a Tree Conditional Random Field (TreeCRF)-based model to apply the SemInfo maximization objective to Probabilistic Context-Free Grammar (PCFG) induction, the state-of-the-art method for unsupervised constituency parsing. Experiments demonstrate that SemInfo correlates more strongly with parsing accuracy than LL. Our algorithm significantly enhances parsing accuracy by an average of 7.85 points across five PCFG variants and in four languages, achieving new state-of-the-art results in three of the four languages.","url_abs":"https://arxiv.org/abs/2410.02558v2","url_pdf":"https://arxiv.org/pdf/2410.02558v2.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":"improving-unsupervised-constituency-parsing","repo_url":"https://github.com/junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"constituency-grammar-induction","task_name":"Constituency Grammar Induction"},{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/constituency-grammar-induction-on-ctb","task":"Constituency Grammar Induction","dataset":"CTB","model":"SemInfo-NPCFG (60NT)","rank_in_archive_order":1,"of":1,"metrics":{"Mean F1":"53.92"},"uses_additional_data":false},{"leaderboard":"/sota/constituency-grammar-induction-on-ptb","task":"Constituency Grammar Induction","dataset":"PTB Diagnostic ECG Database","model":"SemInfo-SCPCFG (1024NT)","rank_in_archive_order":4,"of":24,"metrics":{"Mean F1 (WSJ)":"66.92"},"uses_additional_data":false},{"leaderboard":"/sota/constituency-grammar-induction-on-spmrl","task":"Constituency Grammar Induction","dataset":"SPMRL French","model":"SemInfo-SNPCFG (1024NT)","rank_in_archive_order":1,"of":1,"metrics":{"Mean F1":"54.37"},"uses_additional_data":false},{"leaderboard":"/sota/constituency-grammar-induction-on-spmrl-1","task":"Constituency Grammar Induction","dataset":"SPMRL German","model":"SemInfo-NPCFG (60NT)","rank_in_archive_order":1,"of":1,"metrics":{"Mean F1":"47.77"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.02558","atlas_url":"https://app.syntology.ai/?focus=2410.02558","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.02558"}},"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":"deterministic:regex_extraction","url":"https://github.com/junjiechen-chris/Improving-Unsupervised-Constituency-Parsing-via-Maximizing-Semantic-Information","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/junjiechen-chris/improving-unsupervised-constituency-parsing-via-maximizing-semantic-information","reach":{"status":"ok"}}],"summary":{"ran":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":"1b6c6bc695703c22","entry":"checkpoint","repo":"junjiechen-chris/Improving-Unsupervised-Constituency-Parsing-via-Maximizing-Semantic-Information","repo_kind":"official","path":"parsing_by_maxseminfo/parser/model/SC_PCFG.py","file_url":"https://github.com/junjiechen-chris/Improving-Unsupervised-Constituency-Parsing-via-Maximizing-Semantic-Information/blob/HEAD/parsing_by_maxseminfo/parser/model/SC_PCFG.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1b6c6bc695703c22"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}