{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:44W7PYSDQ53C5BA6MLK4JPBTVV","short_pith_number":"pith:44W7PYSD","schema_version":"1.0","canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","source":{"kind":"arxiv","id":"2406.09717","version":3},"attestation_state":"computed","paper":{"title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Khoi M. Le, Luu Anh Tuan, Trinh Pham","submitted_at":"2024-06-14T04:55:30Z","abstract_excerpt":"In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the opt"},"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":"2406.09717","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-14T04:55:30Z","cross_cats_sorted":[],"title_canon_sha256":"60288cc1a891d535c159f504c940d84d0a1b8f3593844b3192d80821c1ce89ff","abstract_canon_sha256":"d95d0b74b705d343895176cab2280c75b99f8a91579da7808e294b54819dc843"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:38.949048Z","signature_b64":"AL0OOB20uPjJ9aeuJe+aufYzHurd0HwNSMYVYTjBSt+l/MyutHZE1NH4QfQEf0T5EaCrwUJi0jgB7eKkV5DnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e72df7e24387762e841e62d5c4bc33ad4c45bd95e80e9ee74f3338c7b2f44fe6","last_reissued_at":"2026-07-05T08:57:38.948572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:38.948572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniBridge: A Unified Approach to Cross-Lingual Transfer Learning for Low-Resource Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Khoi M. Le, Luu Anh Tuan, Trinh Pham","submitted_at":"2024-06-14T04:55:30Z","abstract_excerpt":"In this paper, we introduce UniBridge (Cross-Lingual Transfer Learning with Optimized Embeddings and Vocabulary), a comprehensive approach developed to improve the effectiveness of Cross-Lingual Transfer Learning, particularly in languages with limited resources. Our approach tackles two essential elements of a language model: the initialization of embeddings and the optimal vocabulary size. Specifically, we propose a novel embedding initialization method that leverages both lexical and semantic alignment for a language. In addition, we present a method for systematically searching for the opt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09717","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.09717/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":"2406.09717","created_at":"2026-07-05T08:57:38.948630+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09717v3","created_at":"2026-07-05T08:57:38.948630+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09717","created_at":"2026-07-05T08:57:38.948630+00:00"},{"alias_kind":"pith_short_12","alias_value":"44W7PYSDQ53C","created_at":"2026-07-05T08:57:38.948630+00:00"},{"alias_kind":"pith_short_16","alias_value":"44W7PYSDQ53C5BA6","created_at":"2026-07-05T08:57:38.948630+00:00"},{"alias_kind":"pith_short_8","alias_value":"44W7PYSD","created_at":"2026-07-05T08:57:38.948630+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/44W7PYSDQ53C5BA6MLK4JPBTVV","json":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV.json","graph_json":"https://pith.science/api/pith-number/44W7PYSDQ53C5BA6MLK4JPBTVV/graph.json","events_json":"https://pith.science/api/pith-number/44W7PYSDQ53C5BA6MLK4JPBTVV/events.json","paper":"https://pith.science/paper/44W7PYSD"},"agent_actions":{"view_html":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV","download_json":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV.json","view_paper":"https://pith.science/paper/44W7PYSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09717&json=true","fetch_graph":"https://pith.science/api/pith-number/44W7PYSDQ53C5BA6MLK4JPBTVV/graph.json","fetch_events":"https://pith.science/api/pith-number/44W7PYSDQ53C5BA6MLK4JPBTVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/action/storage_attestation","attest_author":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/action/author_attestation","sign_citation":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/action/citation_signature","submit_replication":"https://pith.science/pith/44W7PYSDQ53C5BA6MLK4JPBTVV/action/replication_record"}},"created_at":"2026-07-05T08:57:38.948630+00:00","updated_at":"2026-07-05T08:57:38.948630+00:00"}