{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QOIBICERBXOEUPEIFAOWOCQDTP","short_pith_number":"pith:QOIBICER","schema_version":"1.0","canonical_sha256":"83901408910ddc4a3c88281d670a039bd424b70c0d579969d7baa0ef874e30b9","source":{"kind":"arxiv","id":"1908.09659","version":1},"attestation_state":"computed","paper":{"title":"Low-Resource Name Tagging Learned with Weakly Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heng Ji, Tat-Seng Chua, Yixin Cao, Zhiyuan Liu, Zikun hu","submitted_at":"2019-08-26T13:09:37Z","abstract_excerpt":"Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can eff"},"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":"1908.09659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T13:09:37Z","cross_cats_sorted":[],"title_canon_sha256":"9fd095dc8d40398794d81d01d7990a91db2bbd71dd4aaf02213f44f7a0136f0b","abstract_canon_sha256":"493399b494023dcb6d0c0c01ce4a6ae7de55ea780e187c1f0b7561d601c73b6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:42.464931Z","signature_b64":"aGR57Y1AaXZ7kOorUSJ7XjX/Bjr8t1LQjQacXjPbSmbqaANKkkGGu4DNQGndzd3tmQqx1+EtqS6U+KG20co4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83901408910ddc4a3c88281d670a039bd424b70c0d579969d7baa0ef874e30b9","last_reissued_at":"2026-07-04T23:59:42.464544Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:42.464544Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Name Tagging Learned with Weakly Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heng Ji, Tat-Seng Chua, Yixin Cao, Zhiyuan Liu, Zikun hu","submitted_at":"2019-08-26T13:09:37Z","abstract_excerpt":"Name tagging in low-resource languages or domains suffers from inadequate training data. Existing work heavily relies on additional information, while leaving those noisy annotations unexplored that extensively exist on the web. In this paper, we propose a novel neural model for name tagging solely based on weakly labeled (WL) data, so that it can be applied in any low-resource settings. To take the best advantage of all WL sentences, we split them into high-quality and noisy portions for two modules, respectively: (1) a classification module focusing on the large portion of noisy data can eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09659","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/1908.09659/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":"1908.09659","created_at":"2026-07-04T23:59:42.464600+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09659v1","created_at":"2026-07-04T23:59:42.464600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09659","created_at":"2026-07-04T23:59:42.464600+00:00"},{"alias_kind":"pith_short_12","alias_value":"QOIBICERBXOE","created_at":"2026-07-04T23:59:42.464600+00:00"},{"alias_kind":"pith_short_16","alias_value":"QOIBICERBXOEUPEI","created_at":"2026-07-04T23:59:42.464600+00:00"},{"alias_kind":"pith_short_8","alias_value":"QOIBICER","created_at":"2026-07-04T23:59:42.464600+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17715","citing_title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP","json":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP.json","graph_json":"https://pith.science/api/pith-number/QOIBICERBXOEUPEIFAOWOCQDTP/graph.json","events_json":"https://pith.science/api/pith-number/QOIBICERBXOEUPEIFAOWOCQDTP/events.json","paper":"https://pith.science/paper/QOIBICER"},"agent_actions":{"view_html":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP","download_json":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP.json","view_paper":"https://pith.science/paper/QOIBICER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09659&json=true","fetch_graph":"https://pith.science/api/pith-number/QOIBICERBXOEUPEIFAOWOCQDTP/graph.json","fetch_events":"https://pith.science/api/pith-number/QOIBICERBXOEUPEIFAOWOCQDTP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP/action/storage_attestation","attest_author":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP/action/author_attestation","sign_citation":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP/action/citation_signature","submit_replication":"https://pith.science/pith/QOIBICERBXOEUPEIFAOWOCQDTP/action/replication_record"}},"created_at":"2026-07-04T23:59:42.464600+00:00","updated_at":"2026-07-04T23:59:42.464600+00:00"}