{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7RHUK3ZWVHUNJ67HY6LMID5TCI","short_pith_number":"pith:7RHUK3ZW","schema_version":"1.0","canonical_sha256":"fc4f456f36a9e8d4fbe7c796c40fb3122d17231fd148ae4185711da17d0b3125","source":{"kind":"arxiv","id":"1908.05925","version":2},"attestation_state":"computed","paper":{"title":"Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Genta Indra Winata, Pascale Fung, Yan Xu, Zihan Liu","submitted_at":"2019-08-16T10:44:25Z","abstract_excerpt":"This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consist"},"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":"1908.05925","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-16T10:44:25Z","cross_cats_sorted":[],"title_canon_sha256":"59fd0062cab4af589fcf94a1408b2ab39038c63de37af3fd41bcc3d59ffd6755","abstract_canon_sha256":"08689f2098922b0759e6c90e0c54c090999a97e773634691c381cd1a0bbfaa6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:20:01.500385Z","signature_b64":"QynVnLgeFNKivZone4946PpOz1LCdA22EVgiH8sIPyalXWdfRGVdx74bokWdAWeV+UXFIYNtbIRHh6t0ok4DBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc4f456f36a9e8d4fbe7c796c40fb3122d17231fd148ae4185711da17d0b3125","last_reissued_at":"2026-07-05T00:20:01.499919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:20:01.499919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Genta Indra Winata, Pascale Fung, Yan Xu, Zihan Liu","submitted_at":"2019-08-16T10:44:25Z","abstract_excerpt":"This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech. We leverage a phrase-based statistical machine translation (PBSMT) model and a pre-trained language model to combine word-level neural machine translation (NMT) and subword-level NMT models without using any parallel data. We propose to solve the morphological richness problem of languages by training byte-pair encoding (BPE) embeddings for German and Czech separately, and they are aligned using MUSE (Conneau et al., 2018). To ensure the fluency and consist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05925","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1908.05925/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":"1908.05925","created_at":"2026-07-05T00:20:01.499983+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05925v2","created_at":"2026-07-05T00:20:01.499983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05925","created_at":"2026-07-05T00:20:01.499983+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RHUK3ZWVHUN","created_at":"2026-07-05T00:20:01.499983+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RHUK3ZWVHUNJ67H","created_at":"2026-07-05T00:20:01.499983+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RHUK3ZW","created_at":"2026-07-05T00:20:01.499983+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/7RHUK3ZWVHUNJ67HY6LMID5TCI","json":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI.json","graph_json":"https://pith.science/api/pith-number/7RHUK3ZWVHUNJ67HY6LMID5TCI/graph.json","events_json":"https://pith.science/api/pith-number/7RHUK3ZWVHUNJ67HY6LMID5TCI/events.json","paper":"https://pith.science/paper/7RHUK3ZW"},"agent_actions":{"view_html":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI","download_json":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI.json","view_paper":"https://pith.science/paper/7RHUK3ZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05925&json=true","fetch_graph":"https://pith.science/api/pith-number/7RHUK3ZWVHUNJ67HY6LMID5TCI/graph.json","fetch_events":"https://pith.science/api/pith-number/7RHUK3ZWVHUNJ67HY6LMID5TCI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI/action/storage_attestation","attest_author":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI/action/author_attestation","sign_citation":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI/action/citation_signature","submit_replication":"https://pith.science/pith/7RHUK3ZWVHUNJ67HY6LMID5TCI/action/replication_record"}},"created_at":"2026-07-05T00:20:01.499983+00:00","updated_at":"2026-07-05T00:20:01.499983+00:00"}