{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J6CEA5MRQHWPFFKIEGXJVAVZ6G","short_pith_number":"pith:J6CEA5MR","schema_version":"1.0","canonical_sha256":"4f8440759181ecf2954821ae9a82b9f18653d49c14c1e0f339f1bb483cf650b3","source":{"kind":"arxiv","id":"2104.06268","version":1},"attestation_state":"computed","paper":{"title":"Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Genta Indra Winata","submitted_at":"2021-04-13T14:49:26Z","abstract_excerpt":"In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information is judiciously extracted from high-resource monolingual speech data to the code-switching domain. The meta-transfer learning quickly adapts the model to the code-switching task from a number of monolingual tasks by learning to learn in a multi-task learning fashion. Second, we propose a novel multilingual meta-embeddings approach to effectively represent code"},"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":"2104.06268","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-13T14:49:26Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"7efa08b4860e7011742aa1129a4ac528e62521a50579ad164aaab51a92fa37ff","abstract_canon_sha256":"c711c642527beeaadbc21b786c5cd89c85a5cbfd5a422bef78d7140b1eadad24"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:30.502513Z","signature_b64":"8d43uZrc5c/ssg9mLlPGGFQDMD/Aj4AciE/mY8bwUV22apAV31EDMQnESp5eRU0dnoWC4S124b92u5bx4nnSAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f8440759181ecf2954821ae9a82b9f18653d49c14c1e0f339f1bb483cf650b3","last_reissued_at":"2026-07-05T02:31:30.502032Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:30.502032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Transfer Learning for Code-Switched Language and Speech Neural Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.CL","authors_text":"Genta Indra Winata","submitted_at":"2021-04-13T14:49:26Z","abstract_excerpt":"In this thesis, we address the data scarcity and limitations of linguistic theory by proposing language-agnostic multi-task training methods. First, we introduce a meta-learning-based approach, meta-transfer learning, in which information is judiciously extracted from high-resource monolingual speech data to the code-switching domain. The meta-transfer learning quickly adapts the model to the code-switching task from a number of monolingual tasks by learning to learn in a multi-task learning fashion. Second, we propose a novel multilingual meta-embeddings approach to effectively represent code"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06268","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.06268/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":"2104.06268","created_at":"2026-07-05T02:31:30.502091+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06268v1","created_at":"2026-07-05T02:31:30.502091+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06268","created_at":"2026-07-05T02:31:30.502091+00:00"},{"alias_kind":"pith_short_12","alias_value":"J6CEA5MRQHWP","created_at":"2026-07-05T02:31:30.502091+00:00"},{"alias_kind":"pith_short_16","alias_value":"J6CEA5MRQHWPFFKI","created_at":"2026-07-05T02:31:30.502091+00:00"},{"alias_kind":"pith_short_8","alias_value":"J6CEA5MR","created_at":"2026-07-05T02:31:30.502091+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15281","citing_title":"Pre-training a Transformer-Based Generative Model Using a Small Sepedi Dataset","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G","json":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G.json","graph_json":"https://pith.science/api/pith-number/J6CEA5MRQHWPFFKIEGXJVAVZ6G/graph.json","events_json":"https://pith.science/api/pith-number/J6CEA5MRQHWPFFKIEGXJVAVZ6G/events.json","paper":"https://pith.science/paper/J6CEA5MR"},"agent_actions":{"view_html":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G","download_json":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G.json","view_paper":"https://pith.science/paper/J6CEA5MR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06268&json=true","fetch_graph":"https://pith.science/api/pith-number/J6CEA5MRQHWPFFKIEGXJVAVZ6G/graph.json","fetch_events":"https://pith.science/api/pith-number/J6CEA5MRQHWPFFKIEGXJVAVZ6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G/action/storage_attestation","attest_author":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G/action/author_attestation","sign_citation":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G/action/citation_signature","submit_replication":"https://pith.science/pith/J6CEA5MRQHWPFFKIEGXJVAVZ6G/action/replication_record"}},"created_at":"2026-07-05T02:31:30.502091+00:00","updated_at":"2026-07-05T02:31:30.502091+00:00"}