{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DGUA3OHTQCYBDUM64BE7H5PEUF","short_pith_number":"pith:DGUA3OHT","schema_version":"1.0","canonical_sha256":"19a80db8f380b011d19ee049f3f5e4a1595c7a3e2e5ae57e6dd44c4949180ed0","source":{"kind":"arxiv","id":"1710.07045","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pieter Fivez, Simon \\v{S}uster, Walter Daelemans","submitted_at":"2017-10-19T09:15:37Z","abstract_excerpt":"We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. To tune the parameters of this model, we generate self-induced spelling error corpora. We perform our experiments for two languages. For English, we greatly outperform off-the-shelf spelling correction tools on a manually annot"},"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":"1710.07045","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-19T09:15:37Z","cross_cats_sorted":[],"title_canon_sha256":"54e9f42f6506f25addf057b4b533d9880de5a5b1b05cbb703797907e4fa92097","abstract_canon_sha256":"744c46990ade40db94f7b3b82dc8aec808679965ec710a2fe4a0cd3df2a109d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:27.223663Z","signature_b64":"iwdi9XIs1B50oxxtKostyh3LUVADpiP16NwyHE3YHQJeECoSLpC32vyx3qWhUatOXYdFsu0d6/vCdL7sJ9wZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19a80db8f380b011d19ee049f3f5e4a1595c7a3e2e5ae57e6dd44c4949180ed0","last_reissued_at":"2026-05-18T00:32:27.223059Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:27.223059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Context-Sensitive Spelling Correction of English and Dutch Clinical Free-Text with Word and Character N-Gram Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Pieter Fivez, Simon \\v{S}uster, Walter Daelemans","submitted_at":"2017-10-19T09:15:37Z","abstract_excerpt":"We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. To tune the parameters of this model, we generate self-induced spelling error corpora. We perform our experiments for two languages. For English, we greatly outperform off-the-shelf spelling correction tools on a manually annot"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.07045","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":""},"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":"1710.07045","created_at":"2026-05-18T00:32:27.223138+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.07045v1","created_at":"2026-05-18T00:32:27.223138+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.07045","created_at":"2026-05-18T00:32:27.223138+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGUA3OHTQCYB","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGUA3OHTQCYBDUM6","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGUA3OHT","created_at":"2026-05-18T12:31:10.602751+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/DGUA3OHTQCYBDUM64BE7H5PEUF","json":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF.json","graph_json":"https://pith.science/api/pith-number/DGUA3OHTQCYBDUM64BE7H5PEUF/graph.json","events_json":"https://pith.science/api/pith-number/DGUA3OHTQCYBDUM64BE7H5PEUF/events.json","paper":"https://pith.science/paper/DGUA3OHT"},"agent_actions":{"view_html":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF","download_json":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF.json","view_paper":"https://pith.science/paper/DGUA3OHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.07045&json=true","fetch_graph":"https://pith.science/api/pith-number/DGUA3OHTQCYBDUM64BE7H5PEUF/graph.json","fetch_events":"https://pith.science/api/pith-number/DGUA3OHTQCYBDUM64BE7H5PEUF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF/action/storage_attestation","attest_author":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF/action/author_attestation","sign_citation":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF/action/citation_signature","submit_replication":"https://pith.science/pith/DGUA3OHTQCYBDUM64BE7H5PEUF/action/replication_record"}},"created_at":"2026-05-18T00:32:27.223138+00:00","updated_at":"2026-05-18T00:32:27.223138+00:00"}