{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YOOMDMGNMYOX7GAU6JZEJIXVQG","short_pith_number":"pith:YOOMDMGN","schema_version":"1.0","canonical_sha256":"c39cc1b0cd661d7f9814f27244a2f5819c95a0742e485bb415c9ab810714a9c6","source":{"kind":"arxiv","id":"1909.09270","version":1},"attestation_state":"computed","paper":{"title":"Named Entity Recognition with Partially Annotated Training Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen-Tse Tsai, Dan Roth, Snigdha Chaturvedi, Stephen Mayhew","submitted_at":"2019-09-20T00:39:07Z","abstract_excerpt":"Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated. We study the problem of Named Entity Recognition (NER) with partially annotated training data in which a fraction of the named entities are labeled, and all other tokens, entities or otherwise, are labeled as non-entity by default. In order to train on this noisy dataset, we need to distinguish between the true and false negatives. To this end, we introduce a constraint-driven iterative algorithm that learns to detect fal"},"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":"1909.09270","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-09-20T00:39:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"53d9040ef4ee866c95c8ee721341e2f5d8a4aeff048c5d27d622d3745f003109","abstract_canon_sha256":"b1e699833895c9aab7ff1e76a5a59274cfaee2649ba4ed0db603f160e39740c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:05:56.980975Z","signature_b64":"vJN7YLwNRrw7n3d7sGENag4kvF1dkMJLji9qscosQCiGVOpiiO+QwGPg61yW9M7HXxITb+/sYcid18A7GeSrCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c39cc1b0cd661d7f9814f27244a2f5819c95a0742e485bb415c9ab810714a9c6","last_reissued_at":"2026-07-05T00:05:56.980628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:05:56.980628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Named Entity Recognition with Partially Annotated Training Data","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen-Tse Tsai, Dan Roth, Snigdha Chaturvedi, Stephen Mayhew","submitted_at":"2019-09-20T00:39:07Z","abstract_excerpt":"Supervised machine learning assumes the availability of fully-labeled data, but in many cases, such as low-resource languages, the only data available is partially annotated. We study the problem of Named Entity Recognition (NER) with partially annotated training data in which a fraction of the named entities are labeled, and all other tokens, entities or otherwise, are labeled as non-entity by default. In order to train on this noisy dataset, we need to distinguish between the true and false negatives. To this end, we introduce a constraint-driven iterative algorithm that learns to detect fal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.09270","kind":"arxiv","version":1},"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/1909.09270/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":"1909.09270","created_at":"2026-07-05T00:05:56.980680+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.09270v1","created_at":"2026-07-05T00:05:56.980680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.09270","created_at":"2026-07-05T00:05:56.980680+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOOMDMGNMYOX","created_at":"2026-07-05T00:05:56.980680+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOOMDMGNMYOX7GAU","created_at":"2026-07-05T00:05:56.980680+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOOMDMGN","created_at":"2026-07-05T00:05:56.980680+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/YOOMDMGNMYOX7GAU6JZEJIXVQG","json":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG.json","graph_json":"https://pith.science/api/pith-number/YOOMDMGNMYOX7GAU6JZEJIXVQG/graph.json","events_json":"https://pith.science/api/pith-number/YOOMDMGNMYOX7GAU6JZEJIXVQG/events.json","paper":"https://pith.science/paper/YOOMDMGN"},"agent_actions":{"view_html":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG","download_json":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG.json","view_paper":"https://pith.science/paper/YOOMDMGN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.09270&json=true","fetch_graph":"https://pith.science/api/pith-number/YOOMDMGNMYOX7GAU6JZEJIXVQG/graph.json","fetch_events":"https://pith.science/api/pith-number/YOOMDMGNMYOX7GAU6JZEJIXVQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG/action/storage_attestation","attest_author":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG/action/author_attestation","sign_citation":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG/action/citation_signature","submit_replication":"https://pith.science/pith/YOOMDMGNMYOX7GAU6JZEJIXVQG/action/replication_record"}},"created_at":"2026-07-05T00:05:56.980680+00:00","updated_at":"2026-07-05T00:05:56.980680+00:00"}