{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YUBFNSHMFX4QZVO7QPGAGENF6U","short_pith_number":"pith:YUBFNSHM","schema_version":"1.0","canonical_sha256":"c50256c8ec2df90cd5df83cc0311a5f521b7c0dfd0cb79bafa29ea6b2f4b2e97","source":{"kind":"arxiv","id":"2106.09233","version":1},"attestation_state":"computed","paper":{"title":"De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyu Lin, Le Sun, Wenkai Zhang, Xianpei Han","submitted_at":"2021-06-17T04:01:02Z","abstract_excerpt":"Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dic"},"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":"2106.09233","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-17T04:01:02Z","cross_cats_sorted":[],"title_canon_sha256":"a28b4820dc53edbc0972f08c18323df1771ec284e82d1a11c5fcb3992fed260c","abstract_canon_sha256":"2055072155e3bd524b5c6540dba5162274e31234515e61b15470356e8bb2e1fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:13.899420Z","signature_b64":"ktW2OzCYlYCH3F7KZVo7DnJ11WZ3f37zV6Zg5hItfunvBgCLaRLzFG482MMvIamVBAK8tP22dcAdWS/XfVMCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50256c8ec2df90cd5df83cc0311a5f521b7c0dfd0cb79bafa29ea6b2f4b2e97","last_reissued_at":"2026-07-05T02:50:13.899061Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:13.899061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongyu Lin, Le Sun, Wenkai Zhang, Xianpei Han","submitted_at":"2021-06-17T04:01:02Z","abstract_excerpt":"Distant supervision tackles the data bottleneck in NER by automatically generating training instances via dictionary matching. Unfortunately, the learning of DS-NER is severely dictionary-biased, which suffers from spurious correlations and therefore undermines the effectiveness and the robustness of the learned models. In this paper, we fundamentally explain the dictionary bias via a Structural Causal Model (SCM), categorize the bias into intra-dictionary and inter-dictionary biases, and identify their causes. Based on the SCM, we learn de-biased DS-NER via causal interventions. For intra-dic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09233","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/2106.09233/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":"2106.09233","created_at":"2026-07-05T02:50:13.899114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09233v1","created_at":"2026-07-05T02:50:13.899114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09233","created_at":"2026-07-05T02:50:13.899114+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUBFNSHMFX4Q","created_at":"2026-07-05T02:50:13.899114+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUBFNSHMFX4QZVO7","created_at":"2026-07-05T02:50:13.899114+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUBFNSHM","created_at":"2026-07-05T02:50:13.899114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.19346","citing_title":"Semi-Supervised Learning from Small Annotated Data and Large Unlabeled Data for Fine-grained PICO Entity Recognition","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U","json":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U.json","graph_json":"https://pith.science/api/pith-number/YUBFNSHMFX4QZVO7QPGAGENF6U/graph.json","events_json":"https://pith.science/api/pith-number/YUBFNSHMFX4QZVO7QPGAGENF6U/events.json","paper":"https://pith.science/paper/YUBFNSHM"},"agent_actions":{"view_html":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U","download_json":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U.json","view_paper":"https://pith.science/paper/YUBFNSHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09233&json=true","fetch_graph":"https://pith.science/api/pith-number/YUBFNSHMFX4QZVO7QPGAGENF6U/graph.json","fetch_events":"https://pith.science/api/pith-number/YUBFNSHMFX4QZVO7QPGAGENF6U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U/action/storage_attestation","attest_author":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U/action/author_attestation","sign_citation":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U/action/citation_signature","submit_replication":"https://pith.science/pith/YUBFNSHMFX4QZVO7QPGAGENF6U/action/replication_record"}},"created_at":"2026-07-05T02:50:13.899114+00:00","updated_at":"2026-07-05T02:50:13.899114+00:00"}