{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LTX7OYF26MPHGXU5MNBFB7DZJS","short_pith_number":"pith:LTX7OYF2","schema_version":"1.0","canonical_sha256":"5ceff760baf31e735e9d634250fc794c81ce357101a404255195acdb4c9fbbf2","source":{"kind":"arxiv","id":"1906.07286","version":1},"attestation_state":"computed","paper":{"title":"Generalizing Back-Translation in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Julian Schamper, Miguel Gra\\c{c}a, Shahram Khadivi, Yunsu Kim","submitted_at":"2019-06-17T22:13:24Z","abstract_excerpt":"Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabli"},"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":"1906.07286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-17T22:13:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2d02f7bebdb6a163f8c2334dcfe67fa8b7db0f71fc277d430479a8854dfc9323","abstract_canon_sha256":"d2da84ed21878caa1e1137129cda654c7d1dc35868076bf38105635315fd585c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:08.283151Z","signature_b64":"ILCQG9dbSVYw5K8aGIsgOl3H67xGZh3moqY0sboDAgqIW8iJesl3QxWgbp19vRKlsRHo5uzJFL6mpybF67PGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ceff760baf31e735e9d634250fc794c81ce357101a404255195acdb4c9fbbf2","last_reissued_at":"2026-05-17T23:43:08.282669Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:08.282669Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generalizing Back-Translation in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Julian Schamper, Miguel Gra\\c{c}a, Shahram Khadivi, Yunsu Kim","submitted_at":"2019-06-17T22:13:24Z","abstract_excerpt":"Back-translation - data augmentation by translating target monolingual data - is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.07286","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":"1906.07286","created_at":"2026-05-17T23:43:08.282759+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.07286v1","created_at":"2026-05-17T23:43:08.282759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.07286","created_at":"2026-05-17T23:43:08.282759+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTX7OYF26MPH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTX7OYF26MPHGXU5","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTX7OYF2","created_at":"2026-05-18T12:33:21.387695+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/LTX7OYF26MPHGXU5MNBFB7DZJS","json":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS.json","graph_json":"https://pith.science/api/pith-number/LTX7OYF26MPHGXU5MNBFB7DZJS/graph.json","events_json":"https://pith.science/api/pith-number/LTX7OYF26MPHGXU5MNBFB7DZJS/events.json","paper":"https://pith.science/paper/LTX7OYF2"},"agent_actions":{"view_html":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS","download_json":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS.json","view_paper":"https://pith.science/paper/LTX7OYF2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.07286&json=true","fetch_graph":"https://pith.science/api/pith-number/LTX7OYF26MPHGXU5MNBFB7DZJS/graph.json","fetch_events":"https://pith.science/api/pith-number/LTX7OYF26MPHGXU5MNBFB7DZJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS/action/storage_attestation","attest_author":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS/action/author_attestation","sign_citation":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS/action/citation_signature","submit_replication":"https://pith.science/pith/LTX7OYF26MPHGXU5MNBFB7DZJS/action/replication_record"}},"created_at":"2026-05-17T23:43:08.282759+00:00","updated_at":"2026-05-17T23:43:08.282759+00:00"}