{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:QEKBIQXEFRSTC3NAKQNXC52GJI","short_pith_number":"pith:QEKBIQXE","schema_version":"1.0","canonical_sha256":"81141442e42c65316da0541b7177464a1ca4f3d0860768fe13a146223b0baead","source":{"kind":"arxiv","id":"2103.13272","version":2},"attestation_state":"computed","paper":{"title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Feyza Aky\\\"urek, Alexander Gregory Jones, Derry Wijaya, Garry Kuwanto, Isidora Chara Tourni, Siyang Li","submitted_at":"2021-03-24T15:40:28Z","abstract_excerpt":"We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world's languages and the researchers working on these languages. Previously, unsupervised NMT, which employs back-translation (BT) and auto-encoding (AE) tasks has been shown barren for low-resource languages. We demonstrate that leveraging comparable data and code-switching as weak supervision, combined with BT and AE objectives, result in rem"},"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":"2103.13272","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-24T15:40:28Z","cross_cats_sorted":[],"title_canon_sha256":"0833ff4e69e9b6035294f4ccb7b8f792204d34b90dee6486211224b3b469632f","abstract_canon_sha256":"f558e857eab7ce52ee0b8957c3e7492c2cae9fe70c51243df34ea0581a49fc43"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:49.013037Z","signature_b64":"g/VOvvNiSpRPXUNfJVxqsxfJ9poaock/ET3DyfdKmEQmrZesXcu+fN/nybYfyzwjHF3djfvpS+dIugTg+4vLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81141442e42c65316da0541b7177464a1ca4f3d0860768fe13a146223b0baead","last_reissued_at":"2026-07-05T03:35:49.012572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:49.012572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Afra Feyza Aky\\\"urek, Alexander Gregory Jones, Derry Wijaya, Garry Kuwanto, Isidora Chara Tourni, Siyang Li","submitted_at":"2021-03-24T15:40:28Z","abstract_excerpt":"We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world's languages and the researchers working on these languages. Previously, unsupervised NMT, which employs back-translation (BT) and auto-encoding (AE) tasks has been shown barren for low-resource languages. We demonstrate that leveraging comparable data and code-switching as weak supervision, combined with BT and AE objectives, result in rem"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13272","kind":"arxiv","version":2},"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/2103.13272/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":"2103.13272","created_at":"2026-07-05T03:35:49.012629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.13272v2","created_at":"2026-07-05T03:35:49.012629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13272","created_at":"2026-07-05T03:35:49.012629+00:00"},{"alias_kind":"pith_short_12","alias_value":"QEKBIQXEFRST","created_at":"2026-07-05T03:35:49.012629+00:00"},{"alias_kind":"pith_short_16","alias_value":"QEKBIQXEFRSTC3NA","created_at":"2026-07-05T03:35:49.012629+00:00"},{"alias_kind":"pith_short_8","alias_value":"QEKBIQXE","created_at":"2026-07-05T03:35:49.012629+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/QEKBIQXEFRSTC3NAKQNXC52GJI","json":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI.json","graph_json":"https://pith.science/api/pith-number/QEKBIQXEFRSTC3NAKQNXC52GJI/graph.json","events_json":"https://pith.science/api/pith-number/QEKBIQXEFRSTC3NAKQNXC52GJI/events.json","paper":"https://pith.science/paper/QEKBIQXE"},"agent_actions":{"view_html":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI","download_json":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI.json","view_paper":"https://pith.science/paper/QEKBIQXE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.13272&json=true","fetch_graph":"https://pith.science/api/pith-number/QEKBIQXEFRSTC3NAKQNXC52GJI/graph.json","fetch_events":"https://pith.science/api/pith-number/QEKBIQXEFRSTC3NAKQNXC52GJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI/action/storage_attestation","attest_author":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI/action/author_attestation","sign_citation":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI/action/citation_signature","submit_replication":"https://pith.science/pith/QEKBIQXEFRSTC3NAKQNXC52GJI/action/replication_record"}},"created_at":"2026-07-05T03:35:49.012629+00:00","updated_at":"2026-07-05T03:35:49.012629+00:00"}