{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VT3JQR73OBXZW2DZEPYSFF4WEV","short_pith_number":"pith:VT3JQR73","schema_version":"1.0","canonical_sha256":"acf69847fb706f9b687923f122979625479c55592bdb2ec5cc3cde4761aab353","source":{"kind":"arxiv","id":"1804.07755","version":2},"attestation_state":"computed","paper":{"title":"Phrase-Based & Neural Unsupervised Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Guillaume Lample, Ludovic Denoyer, Marc'Aurelio Ranzato, Myle Ott","submitted_at":"2018-04-20T17:59:13Z","abstract_excerpt":"Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs. This work investigates how to learn to translate when having access to only large monolingual corpora in each language. We propose two model variants, a neural and a phrase-based model. Both versions leverage a careful initialization of the parameters, the denoising effect of language models and automatic generation of parallel data by iterative"},"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":"1804.07755","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-20T17:59:13Z","cross_cats_sorted":[],"title_canon_sha256":"83ef7a6b413c61f681e36165d878bdfd4dbd324e636dbe804c2caf4a2b138fbf","abstract_canon_sha256":"2991dbb242906c1ef9046bc0fc420a8bd749989b6806cf6a061161c10936c7dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:08:14.959500Z","signature_b64":"ijwZ1px0Omd2njtKIVys5Pw0XunJXfpS2cxAmXcKySiiYKO7AatPqX1r6qWs0BUW/TYOEaHsgYeq3OnkB4IeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf69847fb706f9b687923f122979625479c55592bdb2ec5cc3cde4761aab353","last_reissued_at":"2026-05-18T00:08:14.959099Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:08:14.959099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Phrase-Based & Neural Unsupervised Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Guillaume Lample, Ludovic Denoyer, Marc'Aurelio Ranzato, Myle Ott","submitted_at":"2018-04-20T17:59:13Z","abstract_excerpt":"Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs. This work investigates how to learn to translate when having access to only large monolingual corpora in each language. We propose two model variants, a neural and a phrase-based model. Both versions leverage a careful initialization of the parameters, the denoising effect of language models and automatic generation of parallel data by iterative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.07755","kind":"arxiv","version":2},"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":"1804.07755","created_at":"2026-05-18T00:08:14.959160+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.07755v2","created_at":"2026-05-18T00:08:14.959160+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.07755","created_at":"2026-05-18T00:08:14.959160+00:00"},{"alias_kind":"pith_short_12","alias_value":"VT3JQR73OBXZ","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VT3JQR73OBXZW2DZ","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VT3JQR73","created_at":"2026-05-18T12:32:59.047623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV","json":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV.json","graph_json":"https://pith.science/api/pith-number/VT3JQR73OBXZW2DZEPYSFF4WEV/graph.json","events_json":"https://pith.science/api/pith-number/VT3JQR73OBXZW2DZEPYSFF4WEV/events.json","paper":"https://pith.science/paper/VT3JQR73"},"agent_actions":{"view_html":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV","download_json":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV.json","view_paper":"https://pith.science/paper/VT3JQR73","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.07755&json=true","fetch_graph":"https://pith.science/api/pith-number/VT3JQR73OBXZW2DZEPYSFF4WEV/graph.json","fetch_events":"https://pith.science/api/pith-number/VT3JQR73OBXZW2DZEPYSFF4WEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV/action/storage_attestation","attest_author":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV/action/author_attestation","sign_citation":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV/action/citation_signature","submit_replication":"https://pith.science/pith/VT3JQR73OBXZW2DZEPYSFF4WEV/action/replication_record"}},"created_at":"2026-05-18T00:08:14.959160+00:00","updated_at":"2026-05-18T00:08:14.959160+00:00"}