{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QNUDEN7NP4BVFZNYBD7TDCUNGP","short_pith_number":"pith:QNUDEN7N","schema_version":"1.0","canonical_sha256":"83683237ed7f0352e5b808ff318a8d33fa2c9081ae521fb49385c4883c9be5ac","source":{"kind":"arxiv","id":"2203.17103","version":1},"attestation_state":"computed","paper":{"title":"$k$NN-NER: Named Entity Recognition with Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guoyin Wang, Jiwei Li, Rongbin Ouyang, Shuhe Wang, Tianwei Zhang, Xiaoya Li, Yuxian Meng","submitted_at":"2022-03-31T15:21:43Z","abstract_excerpt":"Inspired by recent advances in retrieval augmented methods in NLP~\\citep{khandelwal2019generalization,khandelwal2020nearest,meng2021gnn}, in this paper, we introduce a $k$ nearest neighbor NER ($k$NN-NER) framework, which augments the distribution of entity labels by assigning $k$ nearest neighbors retrieved from the training set. This strategy makes the model more capable of handling long-tail cases, along with better few-shot learning abilities. $k$NN-NER requires no additional operation during the training phase, and by interpolating $k$ nearest neighbors search into the vanilla NER model, "},"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":"2203.17103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-31T15:21:43Z","cross_cats_sorted":[],"title_canon_sha256":"632a289cbdeb789d610e90137469c5b5a669789b876d0afee30ad3c85b82d6c2","abstract_canon_sha256":"28ca1aedd76feb1b4a568f69c32c9ff2f148d7a43b1f3505f0fcd943dfefd41b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:10:31.297762Z","signature_b64":"+AI0/hies34Uq5wXt+bKgTkwMMv3cnV2spIlhsCOMpXpOe7+6+qC8rqH+eHYpuaHJ405IKZ6qoEGr18cTOCXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83683237ed7f0352e5b808ff318a8d33fa2c9081ae521fb49385c4883c9be5ac","last_reissued_at":"2026-07-05T04:10:31.297221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:10:31.297221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"$k$NN-NER: Named Entity Recognition with Nearest Neighbor Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guoyin Wang, Jiwei Li, Rongbin Ouyang, Shuhe Wang, Tianwei Zhang, Xiaoya Li, Yuxian Meng","submitted_at":"2022-03-31T15:21:43Z","abstract_excerpt":"Inspired by recent advances in retrieval augmented methods in NLP~\\citep{khandelwal2019generalization,khandelwal2020nearest,meng2021gnn}, in this paper, we introduce a $k$ nearest neighbor NER ($k$NN-NER) framework, which augments the distribution of entity labels by assigning $k$ nearest neighbors retrieved from the training set. This strategy makes the model more capable of handling long-tail cases, along with better few-shot learning abilities. $k$NN-NER requires no additional operation during the training phase, and by interpolating $k$ nearest neighbors search into the vanilla NER model, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17103","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/2203.17103/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":"2203.17103","created_at":"2026-07-05T04:10:31.297278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.17103v1","created_at":"2026-07-05T04:10:31.297278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17103","created_at":"2026-07-05T04:10:31.297278+00:00"},{"alias_kind":"pith_short_12","alias_value":"QNUDEN7NP4BV","created_at":"2026-07-05T04:10:31.297278+00:00"},{"alias_kind":"pith_short_16","alias_value":"QNUDEN7NP4BVFZNY","created_at":"2026-07-05T04:10:31.297278+00:00"},{"alias_kind":"pith_short_8","alias_value":"QNUDEN7N","created_at":"2026-07-05T04:10:31.297278+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/QNUDEN7NP4BVFZNYBD7TDCUNGP","json":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP.json","graph_json":"https://pith.science/api/pith-number/QNUDEN7NP4BVFZNYBD7TDCUNGP/graph.json","events_json":"https://pith.science/api/pith-number/QNUDEN7NP4BVFZNYBD7TDCUNGP/events.json","paper":"https://pith.science/paper/QNUDEN7N"},"agent_actions":{"view_html":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP","download_json":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP.json","view_paper":"https://pith.science/paper/QNUDEN7N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.17103&json=true","fetch_graph":"https://pith.science/api/pith-number/QNUDEN7NP4BVFZNYBD7TDCUNGP/graph.json","fetch_events":"https://pith.science/api/pith-number/QNUDEN7NP4BVFZNYBD7TDCUNGP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP/action/storage_attestation","attest_author":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP/action/author_attestation","sign_citation":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP/action/citation_signature","submit_replication":"https://pith.science/pith/QNUDEN7NP4BVFZNYBD7TDCUNGP/action/replication_record"}},"created_at":"2026-07-05T04:10:31.297278+00:00","updated_at":"2026-07-05T04:10:31.297278+00:00"}