{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6X2QZWE5ZZL62SYD3UH34KGXWS","short_pith_number":"pith:6X2QZWE5","schema_version":"1.0","canonical_sha256":"f5f50cd89dce57ed4b03dd0fbe28d7b4aa04ac8902138ce92c4699216384ccf9","source":{"kind":"arxiv","id":"2109.05003","version":1},"attestation_state":"computed","paper":{"title":"Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Heng Ji, Jiawei Han, Jiaxin Huang, Xuan Wang, Yu Meng, Yunyi Zhang, Yu Zhang","submitted_at":"2021-09-10T17:19:56Z","abstract_excerpt":"We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data"},"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":"2109.05003","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-10T17:19:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1f5cfc68597bd570889adef84c760b8a91733d28b40e60cb5dee9e3e8c5ce7fa","abstract_canon_sha256":"7d295c834c66301f3392e651a10b07e09d12294c26d05039ada8f14370cdf4b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:13:18.326134Z","signature_b64":"geR42qzJJ2OZ7BEpHE6tD9JcmhPiJg6qJTvvt7Y468d//xFVcxmOXwlt6P4P4wlBmnZyBT6sWBjABnQY4e8PCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5f50cd89dce57ed4b03dd0fbe28d7b4aa04ac8902138ce92c4699216384ccf9","last_reissued_at":"2026-07-05T03:13:18.325618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:13:18.325618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distantly-Supervised Named Entity Recognition with Noise-Robust Learning and Language Model Augmented Self-Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Heng Ji, Jiawei Han, Jiaxin Huang, Xuan Wang, Yu Meng, Yunyi Zhang, Yu Zhang","submitted_at":"2021-09-10T17:19:56Z","abstract_excerpt":"We study the problem of training named entity recognition (NER) models using only distantly-labeled data, which can be automatically obtained by matching entity mentions in the raw text with entity types in a knowledge base. The biggest challenge of distantly-supervised NER is that the distant supervision may induce incomplete and noisy labels, rendering the straightforward application of supervised learning ineffective. In this paper, we propose (1) a noise-robust learning scheme comprised of a new loss function and a noisy label removal step, for training NER models on distantly-labeled data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.05003","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/2109.05003/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":"2109.05003","created_at":"2026-07-05T03:13:18.325677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.05003v1","created_at":"2026-07-05T03:13:18.325677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.05003","created_at":"2026-07-05T03:13:18.325677+00:00"},{"alias_kind":"pith_short_12","alias_value":"6X2QZWE5ZZL6","created_at":"2026-07-05T03:13:18.325677+00:00"},{"alias_kind":"pith_short_16","alias_value":"6X2QZWE5ZZL62SYD","created_at":"2026-07-05T03:13:18.325677+00:00"},{"alias_kind":"pith_short_8","alias_value":"6X2QZWE5","created_at":"2026-07-05T03:13:18.325677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.00309","citing_title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","ref_index":293,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS","json":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS.json","graph_json":"https://pith.science/api/pith-number/6X2QZWE5ZZL62SYD3UH34KGXWS/graph.json","events_json":"https://pith.science/api/pith-number/6X2QZWE5ZZL62SYD3UH34KGXWS/events.json","paper":"https://pith.science/paper/6X2QZWE5"},"agent_actions":{"view_html":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS","download_json":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS.json","view_paper":"https://pith.science/paper/6X2QZWE5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.05003&json=true","fetch_graph":"https://pith.science/api/pith-number/6X2QZWE5ZZL62SYD3UH34KGXWS/graph.json","fetch_events":"https://pith.science/api/pith-number/6X2QZWE5ZZL62SYD3UH34KGXWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS/action/storage_attestation","attest_author":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS/action/author_attestation","sign_citation":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS/action/citation_signature","submit_replication":"https://pith.science/pith/6X2QZWE5ZZL62SYD3UH34KGXWS/action/replication_record"}},"created_at":"2026-07-05T03:13:18.325677+00:00","updated_at":"2026-07-05T03:13:18.325677+00:00"}