{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2VHNNPUDYBTZ6OBBZ7KBJEQG2K","short_pith_number":"pith:2VHNNPUD","schema_version":"1.0","canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","source":{"kind":"arxiv","id":"1901.01577","version":1},"attestation_state":"computed","paper":{"title":"Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Julian Schamper, Yunsu Kim","submitted_at":"2019-01-06T17:29:24Z","abstract_excerpt":"We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text or seed lexicon. First, we solve the memory bottleneck and enforce the sparsity with a simple thresholding scheme for the lexicon. Second, we initialize the lexicon training with word classes, which efficiently boosts the performance. Our methods produced promising results on two large-scale unsupervised translation tasks."},"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":"1901.01577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T17:29:24Z","cross_cats_sorted":[],"title_canon_sha256":"5682bb8d99203bd3e12666714c706418d81273e913dd6ef4eb746105cac2da43","abstract_canon_sha256":"3feb6eb65992d39a85d8f9ed4bd0f201923acb1ee5d849712b33bc8f751668d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:51.683037Z","signature_b64":"wCIkMVxlQv9NWhY1d9mOCuEASGsL/8ulUKL+n/FucuJkJwNWbuCvyfPVKInsWth9s3Y7k2n/vaxJAR4OypkWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d54ed6be83c0679f3821cfd4149206d2969c8c3abc6c6adbda900ff5d35627fd","last_reissued_at":"2026-05-17T23:56:51.682650Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:51.682650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Julian Schamper, Yunsu Kim","submitted_at":"2019-01-06T17:29:24Z","abstract_excerpt":"We address for the first time unsupervised training for a translation task with hundreds of thousands of vocabulary words. We scale up the expectation-maximization (EM) algorithm to learn a large translation table without any parallel text or seed lexicon. First, we solve the memory bottleneck and enforce the sparsity with a simple thresholding scheme for the lexicon. Second, we initialize the lexicon training with word classes, which efficiently boosts the performance. Our methods produced promising results on two large-scale unsupervised translation tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01577","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":"1901.01577","created_at":"2026-05-17T23:56:51.682706+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01577v1","created_at":"2026-05-17T23:56:51.682706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01577","created_at":"2026-05-17T23:56:51.682706+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VHNNPUDYBTZ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VHNNPUDYBTZ6OBB","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VHNNPUD","created_at":"2026-05-18T12:33:07.085635+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/2VHNNPUDYBTZ6OBBZ7KBJEQG2K","json":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K.json","graph_json":"https://pith.science/api/pith-number/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/graph.json","events_json":"https://pith.science/api/pith-number/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/events.json","paper":"https://pith.science/paper/2VHNNPUD"},"agent_actions":{"view_html":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K","download_json":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K.json","view_paper":"https://pith.science/paper/2VHNNPUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01577&json=true","fetch_graph":"https://pith.science/api/pith-number/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/graph.json","fetch_events":"https://pith.science/api/pith-number/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/action/storage_attestation","attest_author":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/action/author_attestation","sign_citation":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/action/citation_signature","submit_replication":"https://pith.science/pith/2VHNNPUDYBTZ6OBBZ7KBJEQG2K/action/replication_record"}},"created_at":"2026-05-17T23:56:51.682706+00:00","updated_at":"2026-05-17T23:56:51.682706+00:00"}