{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:P2T5JQDKSSBCNKRUIPGGSKNUP4","short_pith_number":"pith:P2T5JQDK","schema_version":"1.0","canonical_sha256":"7ea7d4c06a948226aa3443cc6929b47f2680570fe59eafca3007c559bb5baf6a","source":{"kind":"arxiv","id":"1903.00149","version":1},"attestation_state":"computed","paper":{"title":"Chinese-Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Longtu Zhang, Mamoru Komachi","submitted_at":"2019-03-01T03:57:15Z","abstract_excerpt":"Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et al., 2018). However, no research has been done to logographic language pairs. This study focuses on Chinese-Japanese UNMT trained by data containing sub-character (ideograph or stroke) level information which is decomposed from character level data. BLEU scores of both character and sub-character level systems were compared against each other and the results s"},"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":"1903.00149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-03-01T03:57:15Z","cross_cats_sorted":[],"title_canon_sha256":"dad140dab8558947112cd5bcf5abe5eb84dbed0213ce31ac6bf05cced9184337","abstract_canon_sha256":"43fb65a5f3f3ac2a22e6adbca2e284ec65d401800dc068c1296ee6483c848896"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:20.738571Z","signature_b64":"2+LDOPe1xVFC8ezhesyMG0UE8CFk3RfF2R8PfylDTOeYneSO/L25eqxuhxgORxCmM7Jcx10MHcE2zgWs9UWYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea7d4c06a948226aa3443cc6929b47f2680570fe59eafca3007c559bb5baf6a","last_reissued_at":"2026-05-17T23:52:20.737801Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:20.737801Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chinese-Japanese Unsupervised Neural Machine Translation Using Sub-character Level Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Longtu Zhang, Mamoru Komachi","submitted_at":"2019-03-01T03:57:15Z","abstract_excerpt":"Unsupervised neural machine translation (UNMT) requires only monolingual data of similar language pairs during training and can produce bi-directional translation models with relatively good performance on alphabetic languages (Lample et al., 2018). However, no research has been done to logographic language pairs. This study focuses on Chinese-Japanese UNMT trained by data containing sub-character (ideograph or stroke) level information which is decomposed from character level data. BLEU scores of both character and sub-character level systems were compared against each other and the results s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00149","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":"1903.00149","created_at":"2026-05-17T23:52:20.737938+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00149v1","created_at":"2026-05-17T23:52:20.737938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00149","created_at":"2026-05-17T23:52:20.737938+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2T5JQDKSSBC","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2T5JQDKSSBCNKRU","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2T5JQDK","created_at":"2026-05-18T12:33:24.271573+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/P2T5JQDKSSBCNKRUIPGGSKNUP4","json":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4.json","graph_json":"https://pith.science/api/pith-number/P2T5JQDKSSBCNKRUIPGGSKNUP4/graph.json","events_json":"https://pith.science/api/pith-number/P2T5JQDKSSBCNKRUIPGGSKNUP4/events.json","paper":"https://pith.science/paper/P2T5JQDK"},"agent_actions":{"view_html":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4","download_json":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4.json","view_paper":"https://pith.science/paper/P2T5JQDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00149&json=true","fetch_graph":"https://pith.science/api/pith-number/P2T5JQDKSSBCNKRUIPGGSKNUP4/graph.json","fetch_events":"https://pith.science/api/pith-number/P2T5JQDKSSBCNKRUIPGGSKNUP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4/action/storage_attestation","attest_author":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4/action/author_attestation","sign_citation":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4/action/citation_signature","submit_replication":"https://pith.science/pith/P2T5JQDKSSBCNKRUIPGGSKNUP4/action/replication_record"}},"created_at":"2026-05-17T23:52:20.737938+00:00","updated_at":"2026-05-17T23:52:20.737938+00:00"}