{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ULWMVHXA3TZJPF7QU3XAVILUHO","short_pith_number":"pith:ULWMVHXA","schema_version":"1.0","canonical_sha256":"a2ecca9ee0dcf29797f0a6ee0aa1743b9033d1983f0f3a3071305516c2cb62a1","source":{"kind":"arxiv","id":"1704.04441","version":1},"attestation_state":"computed","paper":{"title":"How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Georg Heigold, G\\\"unter Neumann, Josef van Genabith","submitted_at":"2017-04-14T14:43:44Z","abstract_excerpt":"This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small changes in the input such as non-canonical input (e.g., typos). Yet both stability and robustness are desired properties in applications involving user-generated content, and the more as humans easily cope with such noisy or adversary conditions. In this paper, we study the impact of noisy input. We consider different noise distributions (one type of noise, combination of noise types) and"},"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":"1704.04441","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-14T14:43:44Z","cross_cats_sorted":[],"title_canon_sha256":"6149c457846b6b6158e63d8225c4a97f99661b219bb5ece05811bd8067be1c8d","abstract_canon_sha256":"04f992bb303d63b9cc1acabe9576d198919d4a7fb8a8d9667fdd864cc8efd312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:21.680835Z","signature_b64":"jS3CoI2mqLcudf4t6xeV0Nf8+WCGszPCiWTU9RnTK5aVHtRfNKQmbHZZ9VSTuCDdIKqYvDZZnGRiuRijZgVqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2ecca9ee0dcf29797f0a6ee0aa1743b9033d1983f0f3a3071305516c2cb62a1","last_reissued_at":"2026-05-18T00:46:21.680493Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:21.680493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Robust Are Character-Based Word Embeddings in Tagging and MT Against Wrod Scramlbing or Randdm Nouse?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Georg Heigold, G\\\"unter Neumann, Josef van Genabith","submitted_at":"2017-04-14T14:43:44Z","abstract_excerpt":"This paper investigates the robustness of NLP against perturbed word forms. While neural approaches can achieve (almost) human-like accuracy for certain tasks and conditions, they often are sensitive to small changes in the input such as non-canonical input (e.g., typos). Yet both stability and robustness are desired properties in applications involving user-generated content, and the more as humans easily cope with such noisy or adversary conditions. In this paper, we study the impact of noisy input. We consider different noise distributions (one type of noise, combination of noise types) and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.04441","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":"1704.04441","created_at":"2026-05-18T00:46:21.680548+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.04441v1","created_at":"2026-05-18T00:46:21.680548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.04441","created_at":"2026-05-18T00:46:21.680548+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULWMVHXA3TZJ","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULWMVHXA3TZJPF7Q","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULWMVHXA","created_at":"2026-05-18T12:31:46.661854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11943","citing_title":"Findings of the First Shared Task on Machine Translation Robustness","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO","json":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO.json","graph_json":"https://pith.science/api/pith-number/ULWMVHXA3TZJPF7QU3XAVILUHO/graph.json","events_json":"https://pith.science/api/pith-number/ULWMVHXA3TZJPF7QU3XAVILUHO/events.json","paper":"https://pith.science/paper/ULWMVHXA"},"agent_actions":{"view_html":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO","download_json":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO.json","view_paper":"https://pith.science/paper/ULWMVHXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.04441&json=true","fetch_graph":"https://pith.science/api/pith-number/ULWMVHXA3TZJPF7QU3XAVILUHO/graph.json","fetch_events":"https://pith.science/api/pith-number/ULWMVHXA3TZJPF7QU3XAVILUHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO/action/storage_attestation","attest_author":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO/action/author_attestation","sign_citation":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO/action/citation_signature","submit_replication":"https://pith.science/pith/ULWMVHXA3TZJPF7QU3XAVILUHO/action/replication_record"}},"created_at":"2026-05-18T00:46:21.680548+00:00","updated_at":"2026-05-18T00:46:21.680548+00:00"}