{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:MFHXH36HU3T4AFWUAQOFGCFT5T","short_pith_number":"pith:MFHXH36H","schema_version":"1.0","canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","source":{"kind":"arxiv","id":"1610.07844","version":1},"attestation_state":"computed","paper":{"title":"Improving historical spelling normalization with bi-directional LSTMs and multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Marcel Bollmann","submitted_at":"2016-10-25T12:30:26Z","abstract_excerpt":"Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data. A common approach is to normalize the spelling of historical words to modern forms. We explore the suitability of a deep neural network architecture for this task, particularly a deep bi-LSTM network applied on a character level. Our model compares well to previously established normalization algorithms when evaluated on a diverse set of texts from Early New High German. We show that multi-task learning with additional normalization data can improve our model's p"},"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":"1610.07844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-10-25T12:30:26Z","cross_cats_sorted":[],"title_canon_sha256":"bb22930c12f8e78d2c8a14fe9d4c9aa44f5c53fb6ce2bdd8a8e2ed476efad9f8","abstract_canon_sha256":"c08e9143f3e8544a02f368deca4b85081e2ebd3fee3ea69fa42ee7ac201c9caf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:01:17.404847Z","signature_b64":"HsPnbPDiLFSqdIkcGP7nu3xqxz+FvN0CZH5k5KHbHQ6KcE/2850eDKwmU5qFoBvznAg4y6Wd47QoeqA+yQFMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"614f73efc7a6e7c016d4041c5308b3ecda597a3ee8c9bef1a56ca3fbc6b51ac3","last_reissued_at":"2026-05-18T01:01:17.404305Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:01:17.404305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving historical spelling normalization with bi-directional LSTMs and multi-task learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anders S{\\o}gaard, Marcel Bollmann","submitted_at":"2016-10-25T12:30:26Z","abstract_excerpt":"Natural-language processing of historical documents is complicated by the abundance of variant spellings and lack of annotated data. A common approach is to normalize the spelling of historical words to modern forms. We explore the suitability of a deep neural network architecture for this task, particularly a deep bi-LSTM network applied on a character level. Our model compares well to previously established normalization algorithms when evaluated on a diverse set of texts from Early New High German. We show that multi-task learning with additional normalization data can improve our model's p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.07844","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":"1610.07844","created_at":"2026-05-18T01:01:17.404412+00:00"},{"alias_kind":"arxiv_version","alias_value":"1610.07844v1","created_at":"2026-05-18T01:01:17.404412+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.07844","created_at":"2026-05-18T01:01:17.404412+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFHXH36HU3T4","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFHXH36HU3T4AFWU","created_at":"2026-05-18T12:30:32.724797+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFHXH36H","created_at":"2026-05-18T12:30:32.724797+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/MFHXH36HU3T4AFWUAQOFGCFT5T","json":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T.json","graph_json":"https://pith.science/api/pith-number/MFHXH36HU3T4AFWUAQOFGCFT5T/graph.json","events_json":"https://pith.science/api/pith-number/MFHXH36HU3T4AFWUAQOFGCFT5T/events.json","paper":"https://pith.science/paper/MFHXH36H"},"agent_actions":{"view_html":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T","download_json":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T.json","view_paper":"https://pith.science/paper/MFHXH36H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1610.07844&json=true","fetch_graph":"https://pith.science/api/pith-number/MFHXH36HU3T4AFWUAQOFGCFT5T/graph.json","fetch_events":"https://pith.science/api/pith-number/MFHXH36HU3T4AFWUAQOFGCFT5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/action/storage_attestation","attest_author":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/action/author_attestation","sign_citation":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/action/citation_signature","submit_replication":"https://pith.science/pith/MFHXH36HU3T4AFWUAQOFGCFT5T/action/replication_record"}},"created_at":"2026-05-18T01:01:17.404412+00:00","updated_at":"2026-05-18T01:01:17.404412+00:00"}