{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4BUYPJOGK3YVYCP6PJMMV4E46Y","short_pith_number":"pith:4BUYPJOG","schema_version":"1.0","canonical_sha256":"e06987a5c656f15c09fe7a58caf09cf6222c6ce6fe5e4f139fb44885cdb76749","source":{"kind":"arxiv","id":"2410.02558","version":3},"attestation_state":"computed","paper":{"title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danushka Bollegala, Junjie Chen, Xiangheng He, Yusuke Miyao","submitted_at":"2024-10-03T15:04:00Z","abstract_excerpt":"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 that trains parsers by maximizing SemInfo, the semantic information encoded in constituent structures. We introduce a bag-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.02558","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T15:04:00Z","cross_cats_sorted":[],"title_canon_sha256":"bd85814fa1804594eb11719048fd0a8063583090691323290124e30b7df4a19d","abstract_canon_sha256":"4d740c07cad912c1e38eee211c458c2853966524eda178a448d1bb6559202560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:18.288201Z","signature_b64":"84y4jmXz2F5W+grSjGLiOlxxHvSJqctw0OCX5DxIH4nwEQrmHhMXEvMwVo1CWllKQ5obaS5eEvrKEYDYBIwBCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e06987a5c656f15c09fe7a58caf09cf6222c6ce6fe5e4f139fb44885cdb76749","last_reissued_at":"2026-07-05T10:44:18.287714Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:18.287714Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Unsupervised Constituency Parsing via Maximizing Semantic Information","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Danushka Bollegala, Junjie Chen, Xiangheng He, Yusuke Miyao","submitted_at":"2024-10-03T15:04:00Z","abstract_excerpt":"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 that trains parsers by maximizing SemInfo, the semantic information encoded in constituent structures. We introduce a bag-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02558","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.02558/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.02558","created_at":"2026-07-05T10:44:18.287770+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02558v3","created_at":"2026-07-05T10:44:18.287770+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02558","created_at":"2026-07-05T10:44:18.287770+00:00"},{"alias_kind":"pith_short_12","alias_value":"4BUYPJOGK3YV","created_at":"2026-07-05T10:44:18.287770+00:00"},{"alias_kind":"pith_short_16","alias_value":"4BUYPJOGK3YVYCP6","created_at":"2026-07-05T10:44:18.287770+00:00"},{"alias_kind":"pith_short_8","alias_value":"4BUYPJOG","created_at":"2026-07-05T10:44:18.287770+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y","json":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y.json","graph_json":"https://pith.science/api/pith-number/4BUYPJOGK3YVYCP6PJMMV4E46Y/graph.json","events_json":"https://pith.science/api/pith-number/4BUYPJOGK3YVYCP6PJMMV4E46Y/events.json","paper":"https://pith.science/paper/4BUYPJOG"},"agent_actions":{"view_html":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y","download_json":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y.json","view_paper":"https://pith.science/paper/4BUYPJOG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02558&json=true","fetch_graph":"https://pith.science/api/pith-number/4BUYPJOGK3YVYCP6PJMMV4E46Y/graph.json","fetch_events":"https://pith.science/api/pith-number/4BUYPJOGK3YVYCP6PJMMV4E46Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y/action/storage_attestation","attest_author":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y/action/author_attestation","sign_citation":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y/action/citation_signature","submit_replication":"https://pith.science/pith/4BUYPJOGK3YVYCP6PJMMV4E46Y/action/replication_record"}},"created_at":"2026-07-05T10:44:18.287770+00:00","updated_at":"2026-07-05T10:44:18.287770+00:00"}