{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SM25Q5AOBTM45H357R3YPTDYME","short_pith_number":"pith:SM25Q5AO","schema_version":"1.0","canonical_sha256":"9335d8740e0cd9ce9f7dfc7787cc7861324588b4b2a972eac53121c21b670809","source":{"kind":"arxiv","id":"2404.05943","version":1},"attestation_state":"computed","paper":{"title":"Interplay of Machine Translation, Diacritics, and Diacritization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ife Adebara, Muhammad Abdul-Mageed, Wei-Rui Chen","submitted_at":"2024-04-09T01:55:05Z","abstract_excerpt":"We investigate two research questions: (1) how do machine translation (MT) and diacritization influence the performance of each other in a multi-task learning setting (2) the effect of keeping (vs. removing) diacritics on MT performance. We examine these two questions in both high-resource (HR) and low-resource (LR) settings across 55 different languages (36 African languages and 19 European languages). For (1), results show that diacritization significantly benefits MT in the LR scenario, doubling or even tripling performance for some languages, but harms MT in the HR scenario. We find that M"},"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":"2404.05943","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-09T01:55:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cb75c00ed8ecc499d0b16b1abf9124933b8a7a49247463f0be4b439671e4f4fd","abstract_canon_sha256":"dd5871d85480aadaf2f3ef5a935ac753adc0662741a3a4694aacbf225391e5f3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:06:01.434694Z","signature_b64":"oxKynrm2iIF73+17H42EYz+ERXMuSgo+43JHv3ah3HGKyRPmiO/6hP7DGdmywFLRjO2MkHUB64t5192ugyroAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9335d8740e0cd9ce9f7dfc7787cc7861324588b4b2a972eac53121c21b670809","last_reissued_at":"2026-07-05T08:06:01.434223Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:06:01.434223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interplay of Machine Translation, Diacritics, and Diacritization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ife Adebara, Muhammad Abdul-Mageed, Wei-Rui Chen","submitted_at":"2024-04-09T01:55:05Z","abstract_excerpt":"We investigate two research questions: (1) how do machine translation (MT) and diacritization influence the performance of each other in a multi-task learning setting (2) the effect of keeping (vs. removing) diacritics on MT performance. We examine these two questions in both high-resource (HR) and low-resource (LR) settings across 55 different languages (36 African languages and 19 European languages). For (1), results show that diacritization significantly benefits MT in the LR scenario, doubling or even tripling performance for some languages, but harms MT in the HR scenario. We find that M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05943","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2404.05943/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2404.05943","created_at":"2026-07-05T08:06:01.434282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05943v1","created_at":"2026-07-05T08:06:01.434282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05943","created_at":"2026-07-05T08:06:01.434282+00:00"},{"alias_kind":"pith_short_12","alias_value":"SM25Q5AOBTM4","created_at":"2026-07-05T08:06:01.434282+00:00"},{"alias_kind":"pith_short_16","alias_value":"SM25Q5AOBTM45H35","created_at":"2026-07-05T08:06:01.434282+00:00"},{"alias_kind":"pith_short_8","alias_value":"SM25Q5AO","created_at":"2026-07-05T08:06:01.434282+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/SM25Q5AOBTM45H357R3YPTDYME","json":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME.json","graph_json":"https://pith.science/api/pith-number/SM25Q5AOBTM45H357R3YPTDYME/graph.json","events_json":"https://pith.science/api/pith-number/SM25Q5AOBTM45H357R3YPTDYME/events.json","paper":"https://pith.science/paper/SM25Q5AO"},"agent_actions":{"view_html":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME","download_json":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME.json","view_paper":"https://pith.science/paper/SM25Q5AO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05943&json=true","fetch_graph":"https://pith.science/api/pith-number/SM25Q5AOBTM45H357R3YPTDYME/graph.json","fetch_events":"https://pith.science/api/pith-number/SM25Q5AOBTM45H357R3YPTDYME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME/action/storage_attestation","attest_author":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME/action/author_attestation","sign_citation":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME/action/citation_signature","submit_replication":"https://pith.science/pith/SM25Q5AOBTM45H357R3YPTDYME/action/replication_record"}},"created_at":"2026-07-05T08:06:01.434282+00:00","updated_at":"2026-07-05T08:06:01.434282+00:00"}