{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QM3KM7IMGCTLPS4XNW3M3ZYECV","short_pith_number":"pith:QM3KM7IM","schema_version":"1.0","canonical_sha256":"8336a67d0c30a6b7cb976db6cde70415471520a22bce0acca997acfe8e8bf855","source":{"kind":"arxiv","id":"1905.09755","version":1},"attestation_state":"computed","paper":{"title":"Misspelling Oblivious Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandra Piktus, Bora Edizel, Edouard Grave, Fabrizio Silvestri, Piotr Bojanowski, Rui Ferreira","submitted_at":"2019-05-23T16:28:08Z","abstract_excerpt":"In this paper we present a method to learn word embeddings that are resilient to misspellings. Existing word embeddings have limited applicability to malformed texts, which contain a non-negligible amount of out-of-vocabulary words. We propose a method combining FastText with subwords and a supervised task of learning misspelling patterns. In our method, misspellings of each word are embedded close to their correct variants. We train these embeddings on a new dataset we are releasing publicly. Finally, we experimentally show the advantages of this approach on both intrinsic and extrinsic NLP t"},"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":"1905.09755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T16:28:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8823293923000556e225e684b87da61c805200802ff708ce9849b1671556fb5","abstract_canon_sha256":"9dc1d3c4f8414b1d86975647ee3299177b99af5bd6ac00b059984209e596c6c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:16.141055Z","signature_b64":"KoYkY5Cvz3QO/7LP/8T++jd5s0uvqDrDF93PEg7MptxXg8paavdRcHHMWzOpHJ6D5QFvm8HiV+CmWToQ3stGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8336a67d0c30a6b7cb976db6cde70415471520a22bce0acca997acfe8e8bf855","last_reissued_at":"2026-05-17T23:45:16.140378Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:16.140378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Misspelling Oblivious Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksandra Piktus, Bora Edizel, Edouard Grave, Fabrizio Silvestri, Piotr Bojanowski, Rui Ferreira","submitted_at":"2019-05-23T16:28:08Z","abstract_excerpt":"In this paper we present a method to learn word embeddings that are resilient to misspellings. Existing word embeddings have limited applicability to malformed texts, which contain a non-negligible amount of out-of-vocabulary words. We propose a method combining FastText with subwords and a supervised task of learning misspelling patterns. In our method, misspellings of each word are embedded close to their correct variants. We train these embeddings on a new dataset we are releasing publicly. Finally, we experimentally show the advantages of this approach on both intrinsic and extrinsic NLP t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09755","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":"1905.09755","created_at":"2026-05-17T23:45:16.140467+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09755v1","created_at":"2026-05-17T23:45:16.140467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09755","created_at":"2026-05-17T23:45:16.140467+00:00"},{"alias_kind":"pith_short_12","alias_value":"QM3KM7IMGCTL","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"QM3KM7IMGCTLPS4X","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"QM3KM7IM","created_at":"2026-05-18T12:33:27.125529+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/QM3KM7IMGCTLPS4XNW3M3ZYECV","json":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV.json","graph_json":"https://pith.science/api/pith-number/QM3KM7IMGCTLPS4XNW3M3ZYECV/graph.json","events_json":"https://pith.science/api/pith-number/QM3KM7IMGCTLPS4XNW3M3ZYECV/events.json","paper":"https://pith.science/paper/QM3KM7IM"},"agent_actions":{"view_html":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV","download_json":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV.json","view_paper":"https://pith.science/paper/QM3KM7IM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09755&json=true","fetch_graph":"https://pith.science/api/pith-number/QM3KM7IMGCTLPS4XNW3M3ZYECV/graph.json","fetch_events":"https://pith.science/api/pith-number/QM3KM7IMGCTLPS4XNW3M3ZYECV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV/action/storage_attestation","attest_author":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV/action/author_attestation","sign_citation":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV/action/citation_signature","submit_replication":"https://pith.science/pith/QM3KM7IMGCTLPS4XNW3M3ZYECV/action/replication_record"}},"created_at":"2026-05-17T23:45:16.140467+00:00","updated_at":"2026-05-17T23:45:16.140467+00:00"}