{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:53W7IJKYWMJPAFNHBAAL6OC6FE","short_pith_number":"pith:53W7IJKY","schema_version":"1.0","canonical_sha256":"eeedf42558b312f015a70800bf385e290745089b2b8d5b8625e3eaf1974caa31","source":{"kind":"arxiv","id":"2505.02463","version":1},"attestation_state":"computed","paper":{"title":"Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela N. Rim, DongNyeong Heo, Heeyoul Choi, Richard Kimera","submitted_at":"2025-05-05T08:47:52Z","abstract_excerpt":"In this paper,we explore the application of Back translation (BT) as a semi-supervised technique to enhance Neural Machine Translation(NMT) models for the English-Luganda language pair, specifically addressing the challenges faced by low-resource languages. The purpose of our study is to demonstrate how BT can mitigate the scarcity of bilingual data by generating synthetic data from monolingual corpora. Our methodology involves developing custom NMT models using both publicly available and web-crawled data, and applying Iterative and Incremental Back translation techniques. We strategically se"},"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":"2505.02463","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-05T08:47:52Z","cross_cats_sorted":[],"title_canon_sha256":"0359788286e8b536b46c625e63a1991133d43f6ff8defed89f91ac9b28bc78b3","abstract_canon_sha256":"4a3fc479903135ba6a542f9b71962cda2a5b16c92fb2d0349700d6e50b7f11cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:37.482305Z","signature_b64":"xefC9BtEL1wmNNaUtP8tR+AIh+9hKqqsrbtcZ/LxqcaCWFAAmNaMpWA9t81dF55VnkWlMsQet39u3HVteVu4CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeedf42558b312f015a70800bf385e290745089b2b8d5b8625e3eaf1974caa31","last_reissued_at":"2026-07-05T10:58:37.481830Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:37.481830Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Augmentation With Back translation for Low Resource languages: A case of English and Luganda","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela N. Rim, DongNyeong Heo, Heeyoul Choi, Richard Kimera","submitted_at":"2025-05-05T08:47:52Z","abstract_excerpt":"In this paper,we explore the application of Back translation (BT) as a semi-supervised technique to enhance Neural Machine Translation(NMT) models for the English-Luganda language pair, specifically addressing the challenges faced by low-resource languages. The purpose of our study is to demonstrate how BT can mitigate the scarcity of bilingual data by generating synthetic data from monolingual corpora. Our methodology involves developing custom NMT models using both publicly available and web-crawled data, and applying Iterative and Incremental Back translation techniques. We strategically se"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02463","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/2505.02463/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":"2505.02463","created_at":"2026-07-05T10:58:37.481897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02463v1","created_at":"2026-07-05T10:58:37.481897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02463","created_at":"2026-07-05T10:58:37.481897+00:00"},{"alias_kind":"pith_short_12","alias_value":"53W7IJKYWMJP","created_at":"2026-07-05T10:58:37.481897+00:00"},{"alias_kind":"pith_short_16","alias_value":"53W7IJKYWMJPAFNH","created_at":"2026-07-05T10:58:37.481897+00:00"},{"alias_kind":"pith_short_8","alias_value":"53W7IJKY","created_at":"2026-07-05T10:58:37.481897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21566","citing_title":"The Saturation Point of Backtranslation in High Quality Low Resource English Gujarati Machine Translation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE","json":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE.json","graph_json":"https://pith.science/api/pith-number/53W7IJKYWMJPAFNHBAAL6OC6FE/graph.json","events_json":"https://pith.science/api/pith-number/53W7IJKYWMJPAFNHBAAL6OC6FE/events.json","paper":"https://pith.science/paper/53W7IJKY"},"agent_actions":{"view_html":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE","download_json":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE.json","view_paper":"https://pith.science/paper/53W7IJKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02463&json=true","fetch_graph":"https://pith.science/api/pith-number/53W7IJKYWMJPAFNHBAAL6OC6FE/graph.json","fetch_events":"https://pith.science/api/pith-number/53W7IJKYWMJPAFNHBAAL6OC6FE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE/action/storage_attestation","attest_author":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE/action/author_attestation","sign_citation":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE/action/citation_signature","submit_replication":"https://pith.science/pith/53W7IJKYWMJPAFNHBAAL6OC6FE/action/replication_record"}},"created_at":"2026-07-05T10:58:37.481897+00:00","updated_at":"2026-07-05T10:58:37.481897+00:00"}