{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2KFDJSERA2PRFD3T7H6U2B2AF7","short_pith_number":"pith:2KFDJSER","schema_version":"1.0","canonical_sha256":"d28a34c891069f128f73f9fd4d07402ff8d47cbddb0733beb86f615400117bca","source":{"kind":"arxiv","id":"1809.01272","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eneko Agirre, Gorka Labaka, Mikel Artetxe","submitted_at":"2018-09-04T23:22:28Z","abstract_excerpt":"While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised counterparts, limiting their practical interest. In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems. Our method profits from the modular "},"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":"1809.01272","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-04T23:22:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b369ef82714d2036f6a44105c0ae5add72902bbcfc0011854f6aacc7a6e0fc95","abstract_canon_sha256":"a9e443c90b58e9bb01ab9be831f90997dfb40dea8008eed13dd88ae1f40ce19d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:33.507078Z","signature_b64":"H7oYjQWoq4vkktj2J/GZhQuCKiK2BF0Rg2oLJunilpK4eWwP4ytfoX0fFa4SfjXxh+stORD9aCzOoJ/8uCytBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d28a34c891069f128f73f9fd4d07402ff8d47cbddb0733beb86f615400117bca","last_reissued_at":"2026-07-05T03:43:33.506620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:33.506620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Statistical Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eneko Agirre, Gorka Labaka, Mikel Artetxe","submitted_at":"2018-09-04T23:22:28Z","abstract_excerpt":"While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised counterparts, limiting their practical interest. In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems. Our method profits from the modular "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01272","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/1809.01272/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":"1809.01272","created_at":"2026-07-05T03:43:33.506680+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01272v1","created_at":"2026-07-05T03:43:33.506680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01272","created_at":"2026-07-05T03:43:33.506680+00:00"},{"alias_kind":"pith_short_12","alias_value":"2KFDJSERA2PR","created_at":"2026-07-05T03:43:33.506680+00:00"},{"alias_kind":"pith_short_16","alias_value":"2KFDJSERA2PRFD3T","created_at":"2026-07-05T03:43:33.506680+00:00"},{"alias_kind":"pith_short_8","alias_value":"2KFDJSER","created_at":"2026-07-05T03:43:33.506680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08174","citing_title":"LLM-BT-Terms: Back-Translation as a Framework for Terminology Standardization and Dynamic Semantic Embedding","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7","json":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7.json","graph_json":"https://pith.science/api/pith-number/2KFDJSERA2PRFD3T7H6U2B2AF7/graph.json","events_json":"https://pith.science/api/pith-number/2KFDJSERA2PRFD3T7H6U2B2AF7/events.json","paper":"https://pith.science/paper/2KFDJSER"},"agent_actions":{"view_html":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7","download_json":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7.json","view_paper":"https://pith.science/paper/2KFDJSER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01272&json=true","fetch_graph":"https://pith.science/api/pith-number/2KFDJSERA2PRFD3T7H6U2B2AF7/graph.json","fetch_events":"https://pith.science/api/pith-number/2KFDJSERA2PRFD3T7H6U2B2AF7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7/action/storage_attestation","attest_author":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7/action/author_attestation","sign_citation":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7/action/citation_signature","submit_replication":"https://pith.science/pith/2KFDJSERA2PRFD3T7H6U2B2AF7/action/replication_record"}},"created_at":"2026-07-05T03:43:33.506680+00:00","updated_at":"2026-07-05T03:43:33.506680+00:00"}