{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:M6WYXFJ4H7QUFADNOO6UMHVA3P","short_pith_number":"pith:M6WYXFJ4","schema_version":"1.0","canonical_sha256":"67ad8b953c3fe142806d73bd461ea0dbceb6de5949fc7bf7dc87767edcb1515e","source":{"kind":"arxiv","id":"1810.12703","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atsushi Fujita, Benjamin Marie","submitted_at":"2018-10-30T12:33:03Z","abstract_excerpt":"Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated architectures that rely on monolingual corpora only. In this work, we propose to define unsupervised NMT (UNMT) as NMT trained with the supervision of synthetic bilingual data. Our approach straightforwardly enables the use of state-of-the-art architectures proposed for supervised NMT by replacing human-made bilingual data with synthetic bilingual data for training. We propose to initialize the training of UNMT with synthetic bilingual data generated "},"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":"1810.12703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-30T12:33:03Z","cross_cats_sorted":[],"title_canon_sha256":"156ffa724e74cbc192cee2e2e89280a6ffd9dca11f3dcfd494b638bfe044003c","abstract_canon_sha256":"f5c7562cf748daff8c2ef47b732d663395ae5f6acb1cbb0dceb8a140d678b7c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:54.370670Z","signature_b64":"IKxPZmOkmtltvWEc+4wa4jKbhGxOanpX4AliCQb024rb0RHJQky5H4yZpVqNFqoH5LxnaMoaNuZEJHmE5oWvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67ad8b953c3fe142806d73bd461ea0dbceb6de5949fc7bf7dc87767edcb1515e","last_reissued_at":"2026-05-18T00:01:54.370213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:54.370213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Atsushi Fujita, Benjamin Marie","submitted_at":"2018-10-30T12:33:03Z","abstract_excerpt":"Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated architectures that rely on monolingual corpora only. In this work, we propose to define unsupervised NMT (UNMT) as NMT trained with the supervision of synthetic bilingual data. Our approach straightforwardly enables the use of state-of-the-art architectures proposed for supervised NMT by replacing human-made bilingual data with synthetic bilingual data for training. We propose to initialize the training of UNMT with synthetic bilingual data generated "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12703","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":"1810.12703","created_at":"2026-05-18T00:01:54.370281+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.12703v1","created_at":"2026-05-18T00:01:54.370281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12703","created_at":"2026-05-18T00:01:54.370281+00:00"},{"alias_kind":"pith_short_12","alias_value":"M6WYXFJ4H7QU","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"M6WYXFJ4H7QUFADN","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"M6WYXFJ4","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2009.10297","citing_title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P","json":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P.json","graph_json":"https://pith.science/api/pith-number/M6WYXFJ4H7QUFADNOO6UMHVA3P/graph.json","events_json":"https://pith.science/api/pith-number/M6WYXFJ4H7QUFADNOO6UMHVA3P/events.json","paper":"https://pith.science/paper/M6WYXFJ4"},"agent_actions":{"view_html":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P","download_json":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P.json","view_paper":"https://pith.science/paper/M6WYXFJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.12703&json=true","fetch_graph":"https://pith.science/api/pith-number/M6WYXFJ4H7QUFADNOO6UMHVA3P/graph.json","fetch_events":"https://pith.science/api/pith-number/M6WYXFJ4H7QUFADNOO6UMHVA3P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P/action/storage_attestation","attest_author":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P/action/author_attestation","sign_citation":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P/action/citation_signature","submit_replication":"https://pith.science/pith/M6WYXFJ4H7QUFADNOO6UMHVA3P/action/replication_record"}},"created_at":"2026-05-18T00:01:54.370281+00:00","updated_at":"2026-05-18T00:01:54.370281+00:00"}