{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ZWKH3YTXB3MC5HFXMPO5QZHJIY","short_pith_number":"pith:ZWKH3YTX","schema_version":"1.0","canonical_sha256":"cd947de2770ed82e9cb763ddd864e94617fd2582dffb60ffa972c6c327c8b3eb","source":{"kind":"arxiv","id":"2109.05112","version":2},"attestation_state":"computed","paper":{"title":"Improved Latent Tree Induction with Distant Supervision via Span Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Drozdov, Andrew McCallum, Dylan Finkbeiner, Jay Yoon Lee, Mohit Iyyer, Shilpa Suresh, Subendhu Rongali, Tim O'Gorman, Zhiyang Xu","submitted_at":"2021-09-10T21:22:09Z","abstract_excerpt":"For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised counterparts to have any practical use as structural annotation of text. In this work, we present a technique that uses distant supervision in the form of span constraints (i.e. phrase bracketing) to improve performance in unsupervised constituency parsing. Using a relatively small number of span constraints we can substantially improve the output from DIORA, "},"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":"2109.05112","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T21:22:09Z","cross_cats_sorted":[],"title_canon_sha256":"d54580c0eea4866bc916ea96a1378dcb6e353dd8b40ff398274fad483e2cd975","abstract_canon_sha256":"c789186e132c53ddd8cac1692854b36bde3dd42e5258e0dabc88a106ac951f9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:58.649956Z","signature_b64":"j/q/X+kZTX2fnc3NI2HyJFBpKC3fHd0R9vxneGxSZNW+5CU1vN1eU3b1vwPLtoBDVKfjrNN63874E4l2pU36DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd947de2770ed82e9cb763ddd864e94617fd2582dffb60ffa972c6c327c8b3eb","last_reissued_at":"2026-07-05T03:27:58.649456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:58.649456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Latent Tree Induction with Distant Supervision via Span Constraints","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrew Drozdov, Andrew McCallum, Dylan Finkbeiner, Jay Yoon Lee, Mohit Iyyer, Shilpa Suresh, Subendhu Rongali, Tim O'Gorman, Zhiyang Xu","submitted_at":"2021-09-10T21:22:09Z","abstract_excerpt":"For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to their supervised counterparts to have any practical use as structural annotation of text. In this work, we present a technique that uses distant supervision in the form of span constraints (i.e. phrase bracketing) to improve performance in unsupervised constituency parsing. Using a relatively small number of span constraints we can substantially improve the output from DIORA, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05112","kind":"arxiv","version":2},"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/2109.05112/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":"2109.05112","created_at":"2026-07-05T03:27:58.649513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05112v2","created_at":"2026-07-05T03:27:58.649513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05112","created_at":"2026-07-05T03:27:58.649513+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWKH3YTXB3MC","created_at":"2026-07-05T03:27:58.649513+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWKH3YTXB3MC5HFX","created_at":"2026-07-05T03:27:58.649513+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWKH3YTX","created_at":"2026-07-05T03:27:58.649513+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/ZWKH3YTXB3MC5HFXMPO5QZHJIY","json":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY.json","graph_json":"https://pith.science/api/pith-number/ZWKH3YTXB3MC5HFXMPO5QZHJIY/graph.json","events_json":"https://pith.science/api/pith-number/ZWKH3YTXB3MC5HFXMPO5QZHJIY/events.json","paper":"https://pith.science/paper/ZWKH3YTX"},"agent_actions":{"view_html":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY","download_json":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY.json","view_paper":"https://pith.science/paper/ZWKH3YTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05112&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWKH3YTXB3MC5HFXMPO5QZHJIY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWKH3YTXB3MC5HFXMPO5QZHJIY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY/action/storage_attestation","attest_author":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY/action/author_attestation","sign_citation":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY/action/citation_signature","submit_replication":"https://pith.science/pith/ZWKH3YTXB3MC5HFXMPO5QZHJIY/action/replication_record"}},"created_at":"2026-07-05T03:27:58.649513+00:00","updated_at":"2026-07-05T03:27:58.649513+00:00"}