{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:IMB6CTUGE232XSODFEBVOJLZEQ","short_pith_number":"pith:IMB6CTUG","schema_version":"1.0","canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","source":{"kind":"arxiv","id":"1604.02201","version":1},"attestation_state":"computed","paper":{"title":"Transfer Learning for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight","submitted_at":"2016-04-08T00:16:35Z","abstract_excerpt":"The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we improve baseline NMT models by an average of 5.6 Bleu on four l"},"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":"1604.02201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-08T00:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"5c27510fb659f24b98659e765b6e76f2f1e40a948f2741192809cb4cd809b3c9","abstract_canon_sha256":"e9cc69d08b93f8c7f3e3cfa903f45876b132f9feee29181f1bcdca3cf5d5eab9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:28.235768Z","signature_b64":"s3jUeRgU5V5vqADWD7yN5FbsHorHRkdH8GZUl/su3eEpGj36JYz1zbwWOKvIkWYwu4CHuiAyrJMg/3n9tbI+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","last_reissued_at":"2026-05-18T01:17:28.235108Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:28.235108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transfer Learning for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight","submitted_at":"2016-04-08T00:16:35Z","abstract_excerpt":"The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we improve baseline NMT models by an average of 5.6 Bleu on four l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02201","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":"1604.02201","created_at":"2026-05-18T01:17:28.235208+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.02201v1","created_at":"2026-05-18T01:17:28.235208+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02201","created_at":"2026-05-18T01:17:28.235208+00:00"},{"alias_kind":"pith_short_12","alias_value":"IMB6CTUGE232","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_16","alias_value":"IMB6CTUGE232XSOD","created_at":"2026-05-18T12:30:22.444734+00:00"},{"alias_kind":"pith_short_8","alias_value":"IMB6CTUG","created_at":"2026-05-18T12:30:22.444734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.16621","citing_title":"The Role of Vocabularies in Learning Sparse Representations for Ranking","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ","json":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ.json","graph_json":"https://pith.science/api/pith-number/IMB6CTUGE232XSODFEBVOJLZEQ/graph.json","events_json":"https://pith.science/api/pith-number/IMB6CTUGE232XSODFEBVOJLZEQ/events.json","paper":"https://pith.science/paper/IMB6CTUG"},"agent_actions":{"view_html":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ","download_json":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ.json","view_paper":"https://pith.science/paper/IMB6CTUG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.02201&json=true","fetch_graph":"https://pith.science/api/pith-number/IMB6CTUGE232XSODFEBVOJLZEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IMB6CTUGE232XSODFEBVOJLZEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/action/storage_attestation","attest_author":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/action/author_attestation","sign_citation":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/action/citation_signature","submit_replication":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/action/replication_record"}},"created_at":"2026-05-18T01:17:28.235208+00:00","updated_at":"2026-05-18T01:17:28.235208+00:00"}