{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:L2NGI737D3G4XQNUHWYM3Z7GHH","short_pith_number":"pith:L2NGI737","schema_version":"1.0","canonical_sha256":"5e9a647f7f1ecdcbc1b43db0cde7e639c78b3cd2971ff099e27da3c26f761fd2","source":{"kind":"arxiv","id":"1909.00180","version":1},"attestation_state":"computed","paper":{"title":"Explicit Cross-lingual Pre-training for Unsupervised Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Zhou, Shuai Ma, Shujie Liu, Shuo Ren, Yu Wu","submitted_at":"2019-08-31T09:58:57Z","abstract_excerpt":"Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is inexplicit and limited. In this paper, we propose a novel cross-lingual pre-training method for unsupervised machine translation by incorporating explicit cross-lingual training signals. Specifically, we first calculate cross-lingual n-gram embeddings and infer an n-gram translation table from them. With those n-gram translation pairs, we propose a new pre-training m"},"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":"1909.00180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-31T09:58:57Z","cross_cats_sorted":[],"title_canon_sha256":"b305b76ef52175216cdebebc669e98bdbaa8b66fdb1fd39fbabf5bb278b87126","abstract_canon_sha256":"516734b724cfdefd5b5bb60fa565a8a2ce8b6480dc5a19a737f6fde0e970d7e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:01:06.484237Z","signature_b64":"BRFnZA8iLu0eYhoH3QQs1wV4ufe5Qi9Y2h6J/Cy3V/RuhSDCw+/KYorth9ETg5lVKToPfvZ7yQKkRe6vsVwAAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e9a647f7f1ecdcbc1b43db0cde7e639c78b3cd2971ff099e27da3c26f761fd2","last_reissued_at":"2026-07-05T00:01:06.483901Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:01:06.483901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explicit Cross-lingual Pre-training for Unsupervised Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Zhou, Shuai Ma, Shujie Liu, Shuo Ren, Yu Wu","submitted_at":"2019-08-31T09:58:57Z","abstract_excerpt":"Pre-training has proven to be effective in unsupervised machine translation due to its ability to model deep context information in cross-lingual scenarios. However, the cross-lingual information obtained from shared BPE spaces is inexplicit and limited. In this paper, we propose a novel cross-lingual pre-training method for unsupervised machine translation by incorporating explicit cross-lingual training signals. Specifically, we first calculate cross-lingual n-gram embeddings and infer an n-gram translation table from them. With those n-gram translation pairs, we propose a new pre-training m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.00180","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/1909.00180/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":"1909.00180","created_at":"2026-07-05T00:01:06.483958+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.00180v1","created_at":"2026-07-05T00:01:06.483958+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.00180","created_at":"2026-07-05T00:01:06.483958+00:00"},{"alias_kind":"pith_short_12","alias_value":"L2NGI737D3G4","created_at":"2026-07-05T00:01:06.483958+00:00"},{"alias_kind":"pith_short_16","alias_value":"L2NGI737D3G4XQNU","created_at":"2026-07-05T00:01:06.483958+00:00"},{"alias_kind":"pith_short_8","alias_value":"L2NGI737","created_at":"2026-07-05T00:01:06.483958+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/L2NGI737D3G4XQNUHWYM3Z7GHH","json":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH.json","graph_json":"https://pith.science/api/pith-number/L2NGI737D3G4XQNUHWYM3Z7GHH/graph.json","events_json":"https://pith.science/api/pith-number/L2NGI737D3G4XQNUHWYM3Z7GHH/events.json","paper":"https://pith.science/paper/L2NGI737"},"agent_actions":{"view_html":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH","download_json":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH.json","view_paper":"https://pith.science/paper/L2NGI737","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.00180&json=true","fetch_graph":"https://pith.science/api/pith-number/L2NGI737D3G4XQNUHWYM3Z7GHH/graph.json","fetch_events":"https://pith.science/api/pith-number/L2NGI737D3G4XQNUHWYM3Z7GHH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH/action/storage_attestation","attest_author":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH/action/author_attestation","sign_citation":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH/action/citation_signature","submit_replication":"https://pith.science/pith/L2NGI737D3G4XQNUHWYM3Z7GHH/action/replication_record"}},"created_at":"2026-07-05T00:01:06.483958+00:00","updated_at":"2026-07-05T00:01:06.483958+00:00"}