{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:ABZXPICIJY2OFPGIBX64Y77EML","short_pith_number":"pith:ABZXPICI","schema_version":"1.0","canonical_sha256":"007377a0484e34e2bcc80dfdcc7fe462dc27be03cb806bd8eb419fe49947c5e6","source":{"kind":"arxiv","id":"1710.04087","version":3},"attestation_state":"computed","paper":{"title":"Word Translation Without Parallel Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Guillaume Lample, Herv\\'e J\\'egou, Ludovic Denoyer, Marc'Aurelio Ranzato","submitted_at":"2017-10-11T14:24:28Z","abstract_excerpt":"State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised w"},"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":"1710.04087","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-11T14:24:28Z","cross_cats_sorted":[],"title_canon_sha256":"ea2260635ba6a11ad7962e050c5017b15bfd389562af4c61056ac1982dbce221","abstract_canon_sha256":"82f117ffd74eef759b436509ab55797d739ae137f96e5df26bca5ba4d71f9d92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:51.119595Z","signature_b64":"wnD1AWx3A7q/0YQNqj1oblRXxVcqJ0KyeDRLqbZEaaymbC0hVwk+ogN5/gcrln+Stas30+b5bQrA0VXB0qFZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"007377a0484e34e2bcc80dfdcc7fe462dc27be03cb806bd8eb419fe49947c5e6","last_reissued_at":"2026-05-18T00:24:51.118890Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:51.118890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word Translation Without Parallel Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Guillaume Lample, Herv\\'e J\\'egou, Ludovic Denoyer, Marc'Aurelio Ranzato","submitted_at":"2017-10-11T14:24:28Z","abstract_excerpt":"State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04087","kind":"arxiv","version":3},"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":"1710.04087","created_at":"2026-05-18T00:24:51.119004+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.04087v3","created_at":"2026-05-18T00:24:51.119004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04087","created_at":"2026-05-18T00:24:51.119004+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABZXPICIJY2O","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABZXPICIJY2OFPGI","created_at":"2026-05-18T12:31:05.417338+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABZXPICI","created_at":"2026-05-18T12:31:05.417338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2507.20906","citing_title":"Soft Head Selection for Injecting ICL-Derived Task Embeddings","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2009.10297","citing_title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML","json":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML.json","graph_json":"https://pith.science/api/pith-number/ABZXPICIJY2OFPGIBX64Y77EML/graph.json","events_json":"https://pith.science/api/pith-number/ABZXPICIJY2OFPGIBX64Y77EML/events.json","paper":"https://pith.science/paper/ABZXPICI"},"agent_actions":{"view_html":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML","download_json":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML.json","view_paper":"https://pith.science/paper/ABZXPICI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.04087&json=true","fetch_graph":"https://pith.science/api/pith-number/ABZXPICIJY2OFPGIBX64Y77EML/graph.json","fetch_events":"https://pith.science/api/pith-number/ABZXPICIJY2OFPGIBX64Y77EML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML/action/storage_attestation","attest_author":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML/action/author_attestation","sign_citation":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML/action/citation_signature","submit_replication":"https://pith.science/pith/ABZXPICIJY2OFPGIBX64Y77EML/action/replication_record"}},"created_at":"2026-05-18T00:24:51.119004+00:00","updated_at":"2026-05-18T00:24:51.119004+00:00"}