{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UUKNAYXVYN4XH73FZ5HHL22H2T","short_pith_number":"pith:UUKNAYXV","schema_version":"1.0","canonical_sha256":"a514d062f5c37973ff65cf4e75eb47d4cd4e862cf3bb18fb5ab49c84722bea61","source":{"kind":"arxiv","id":"1901.01590","version":1},"attestation_state":"computed","paper":{"title":"Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Jiahui Geng, Yunsu Kim","submitted_at":"2019-01-06T18:30:50Z","abstract_excerpt":"Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve word-by-word translation of cross-lingual embeddings, using only monolingual corpora but without any back-translation. We integrate a language model for context-aware search, and use a novel denoising autoencoder to handle reordering. Our system surpasses state-of-the-art unsupervised neural translation systems without costly iterative training. We also analyze the eff"},"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":"1901.01590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-06T18:30:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fa60c904c3f1d04aa6465223f28c04136b99d77523e6a390020a40174537f44","abstract_canon_sha256":"821271167673420c0a34a6c3562e3272af80ac1e9381bfe07b0f7b3cbce4b531"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:51.665954Z","signature_b64":"NApJPqlF9OhppRgjUU+mt/y3Rw6211ODUVPxJ68hC2cf3bjEhpTBQx+32gk4fgq+2lxgBqSeFzo/ocvGARcTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a514d062f5c37973ff65cf4e75eb47d4cd4e862cf3bb18fb5ab49c84722bea61","last_reissued_at":"2026-05-17T23:56:51.665471Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:51.665471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Hermann Ney, Jiahui Geng, Yunsu Kim","submitted_at":"2019-01-06T18:30:50Z","abstract_excerpt":"Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve word-by-word translation of cross-lingual embeddings, using only monolingual corpora but without any back-translation. We integrate a language model for context-aware search, and use a novel denoising autoencoder to handle reordering. Our system surpasses state-of-the-art unsupervised neural translation systems without costly iterative training. We also analyze the eff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.01590","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":"1901.01590","created_at":"2026-05-17T23:56:51.665551+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.01590v1","created_at":"2026-05-17T23:56:51.665551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.01590","created_at":"2026-05-17T23:56:51.665551+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUKNAYXVYN4X","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUKNAYXVYN4XH73F","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUKNAYXV","created_at":"2026-05-18T12:33:30.264802+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/UUKNAYXVYN4XH73FZ5HHL22H2T","json":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T.json","graph_json":"https://pith.science/api/pith-number/UUKNAYXVYN4XH73FZ5HHL22H2T/graph.json","events_json":"https://pith.science/api/pith-number/UUKNAYXVYN4XH73FZ5HHL22H2T/events.json","paper":"https://pith.science/paper/UUKNAYXV"},"agent_actions":{"view_html":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T","download_json":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T.json","view_paper":"https://pith.science/paper/UUKNAYXV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.01590&json=true","fetch_graph":"https://pith.science/api/pith-number/UUKNAYXVYN4XH73FZ5HHL22H2T/graph.json","fetch_events":"https://pith.science/api/pith-number/UUKNAYXVYN4XH73FZ5HHL22H2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T/action/storage_attestation","attest_author":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T/action/author_attestation","sign_citation":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T/action/citation_signature","submit_replication":"https://pith.science/pith/UUKNAYXVYN4XH73FZ5HHL22H2T/action/replication_record"}},"created_at":"2026-05-17T23:56:51.665551+00:00","updated_at":"2026-05-17T23:56:51.665551+00:00"}