{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RNPBKDGZQFLE3FZ4ZZJOOWG3ZC","short_pith_number":"pith:RNPBKDGZ","schema_version":"1.0","canonical_sha256":"8b5e150cd981564d973cce52e758dbc8be45baa9b07b171b4b847691086eef02","source":{"kind":"arxiv","id":"1909.03750","version":1},"attestation_state":"computed","paper":{"title":"Combining SMT and NMT Back-Translated Data for Efficient NMT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Andy Way, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Maja Popovic","submitted_at":"2019-09-09T10:45:05Z","abstract_excerpt":"Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is back-translation (Sennrich et al., 2016), which consists on generating synthetic sentences by translating a set of monolingual, target-language sentences using a Machine Translation (MT) model.\n  Generally, NMT models are used for back-translation. In this work, we analyze the performance of models when the training data is extended with synthetic data using d"},"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":"1909.03750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-09T10:45:05Z","cross_cats_sorted":[],"title_canon_sha256":"f3d2cad5f53d5d82e5168a4d93ac5fcdb16f42af7b33475b0891a854b8a31fea","abstract_canon_sha256":"9dc68945ba73f4793682ba766a11c5c32f9f30fe43b7ebca356ba93dc1f08a1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:08.415702Z","signature_b64":"ChXb8FMJAMClaFK7RW8Xv47+fWLOxQh/LQkBvH7AO3pQTHiB+W6Nn23/QLzx7Vda5gcSa+TFExrkx0VbfSxBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b5e150cd981564d973cce52e758dbc8be45baa9b07b171b4b847691086eef02","last_reissued_at":"2026-07-05T00:03:08.415284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:08.415284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Combining SMT and NMT Back-Translated Data for Efficient NMT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Andy Way, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Maja Popovic","submitted_at":"2019-09-09T10:45:05Z","abstract_excerpt":"Neural Machine Translation (NMT) models achieve their best performance when large sets of parallel data are used for training. Consequently, techniques for augmenting the training set have become popular recently. One of these methods is back-translation (Sennrich et al., 2016), which consists on generating synthetic sentences by translating a set of monolingual, target-language sentences using a Machine Translation (MT) model.\n  Generally, NMT models are used for back-translation. In this work, we analyze the performance of models when the training data is extended with synthetic data using d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03750","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/1909.03750/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":"1909.03750","created_at":"2026-07-05T00:03:08.415342+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.03750v1","created_at":"2026-07-05T00:03:08.415342+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03750","created_at":"2026-07-05T00:03:08.415342+00:00"},{"alias_kind":"pith_short_12","alias_value":"RNPBKDGZQFLE","created_at":"2026-07-05T00:03:08.415342+00:00"},{"alias_kind":"pith_short_16","alias_value":"RNPBKDGZQFLE3FZ4","created_at":"2026-07-05T00:03:08.415342+00:00"},{"alias_kind":"pith_short_8","alias_value":"RNPBKDGZ","created_at":"2026-07-05T00:03:08.415342+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/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC","json":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC.json","graph_json":"https://pith.science/api/pith-number/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/graph.json","events_json":"https://pith.science/api/pith-number/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/events.json","paper":"https://pith.science/paper/RNPBKDGZ"},"agent_actions":{"view_html":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC","download_json":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC.json","view_paper":"https://pith.science/paper/RNPBKDGZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.03750&json=true","fetch_graph":"https://pith.science/api/pith-number/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/action/storage_attestation","attest_author":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/action/author_attestation","sign_citation":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/action/citation_signature","submit_replication":"https://pith.science/pith/RNPBKDGZQFLE3FZ4ZZJOOWG3ZC/action/replication_record"}},"created_at":"2026-07-05T00:03:08.415342+00:00","updated_at":"2026-07-05T00:03:08.415342+00:00"}