{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:QM3KM7IMGCTLPS4XNW3M3ZYECV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9dc1d3c4f8414b1d86975647ee3299177b99af5bd6ac00b059984209e596c6c8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T16:28:08Z","title_canon_sha256":"f8823293923000556e225e684b87da61c805200802ff708ce9849b1671556fb5"},"schema_version":"1.0","source":{"id":"1905.09755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.09755","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"arxiv_version","alias_value":"1905.09755v1","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09755","created_at":"2026-05-17T23:45:16Z"},{"alias_kind":"pith_short_12","alias_value":"QM3KM7IMGCTL","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"QM3KM7IMGCTLPS4X","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"QM3KM7IM","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:68f8c89fc6b60940db53763b561faa174c0f66de7686cca34a42912dd4fe65e8","target":"graph","created_at":"2026-05-17T23:45:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Aleksandra Piktus, Bora Edizel, Edouard Grave, Fabrizio Silvestri, Piotr Bojanowski, Rui Ferreira","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T16:28:08Z","title":"Misspelling Oblivious Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09755","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:728cc70ed70ed8127dfcc9fbd1eb12a16e7b255728f78d9c817a62a3df04f12b","target":"record","created_at":"2026-05-17T23:45:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9dc1d3c4f8414b1d86975647ee3299177b99af5bd6ac00b059984209e596c6c8","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-23T16:28:08Z","title_canon_sha256":"f8823293923000556e225e684b87da61c805200802ff708ce9849b1671556fb5"},"schema_version":"1.0","source":{"id":"1905.09755","kind":"arxiv","version":1}},"canonical_sha256":"8336a67d0c30a6b7cb976db6cde70415471520a22bce0acca997acfe8e8bf855","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8336a67d0c30a6b7cb976db6cde70415471520a22bce0acca997acfe8e8bf855","first_computed_at":"2026-05-17T23:45:16.140378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:16.140378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KoYkY5Cvz3QO/7LP/8T++jd5s0uvqDrDF93PEg7MptxXg8paavdRcHHMWzOpHJ6D5QFvm8HiV+CmWToQ3stGAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:16.141055Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.09755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:728cc70ed70ed8127dfcc9fbd1eb12a16e7b255728f78d9c817a62a3df04f12b","sha256:68f8c89fc6b60940db53763b561faa174c0f66de7686cca34a42912dd4fe65e8"],"state_sha256":"e0e2d340a33eca9591bd193b26a89cb26dc788c94289be754ac5939a43cb305f"}