{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UZF6WK6WLTYUJS32FXWKMGOUKY","short_pith_number":"pith:UZF6WK6W","schema_version":"1.0","canonical_sha256":"a64beb2bd65cf144cb7a2deca619d45615ca6361afa5c8d4b3de442cdba60e9e","source":{"kind":"arxiv","id":"1903.03243","version":2},"attestation_state":"computed","paper":{"title":"Context-Aware Cross-Lingual Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanan Aldarmaki, Mona Diab","submitted_at":"2019-03-08T01:46:37Z","abstract_excerpt":"Cross-lingual word vectors are typically obtained by fitting an orthogonal matrix that maps the entries of a bilingual dictionary from a source to a target vector space. Word vectors, however, are most commonly used for sentence or document-level representations that are calculated as the weighted average of word embeddings. In this paper, we propose an alternative to word-level mapping that better reflects sentence-level cross-lingual similarity. We incorporate context in the transformation matrix by directly mapping the averaged embeddings of aligned sentences in a parallel corpus. We also i"},"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":"1903.03243","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-08T01:46:37Z","cross_cats_sorted":[],"title_canon_sha256":"f7f41ac4a0dd663679e8bef4fe0314fcd5260970a5c9e094e4dbd4511e18f1c3","abstract_canon_sha256":"a6332bf7ea909b332c27cdd4ddb5cfbc0fc01a2a0b0406690f994f67760608d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:49.858684Z","signature_b64":"S186ekI7htfQLnpyhqrKonrhPfKVJTP9nXPVXqs8+1qYWlPeUWl99w8nZlI8SIGv0vUmAU/hWvYpF1d9Fo6gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a64beb2bd65cf144cb7a2deca619d45615ca6361afa5c8d4b3de442cdba60e9e","last_reissued_at":"2026-05-17T23:49:49.858142Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:49.858142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Context-Aware Cross-Lingual Mapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanan Aldarmaki, Mona Diab","submitted_at":"2019-03-08T01:46:37Z","abstract_excerpt":"Cross-lingual word vectors are typically obtained by fitting an orthogonal matrix that maps the entries of a bilingual dictionary from a source to a target vector space. Word vectors, however, are most commonly used for sentence or document-level representations that are calculated as the weighted average of word embeddings. In this paper, we propose an alternative to word-level mapping that better reflects sentence-level cross-lingual similarity. We incorporate context in the transformation matrix by directly mapping the averaged embeddings of aligned sentences in a parallel corpus. We also i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03243","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":""},"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":"1903.03243","created_at":"2026-05-17T23:49:49.858245+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.03243v2","created_at":"2026-05-17T23:49:49.858245+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03243","created_at":"2026-05-17T23:49:49.858245+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZF6WK6WLTYU","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZF6WK6WLTYUJS32","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZF6WK6W","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/UZF6WK6WLTYUJS32FXWKMGOUKY","json":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY.json","graph_json":"https://pith.science/api/pith-number/UZF6WK6WLTYUJS32FXWKMGOUKY/graph.json","events_json":"https://pith.science/api/pith-number/UZF6WK6WLTYUJS32FXWKMGOUKY/events.json","paper":"https://pith.science/paper/UZF6WK6W"},"agent_actions":{"view_html":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY","download_json":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY.json","view_paper":"https://pith.science/paper/UZF6WK6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.03243&json=true","fetch_graph":"https://pith.science/api/pith-number/UZF6WK6WLTYUJS32FXWKMGOUKY/graph.json","fetch_events":"https://pith.science/api/pith-number/UZF6WK6WLTYUJS32FXWKMGOUKY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY/action/storage_attestation","attest_author":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY/action/author_attestation","sign_citation":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY/action/citation_signature","submit_replication":"https://pith.science/pith/UZF6WK6WLTYUJS32FXWKMGOUKY/action/replication_record"}},"created_at":"2026-05-17T23:49:49.858245+00:00","updated_at":"2026-05-17T23:49:49.858245+00:00"}