{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AS3Y7QYRYQEL55TP5EKQYLNEAD","short_pith_number":"pith:AS3Y7QYR","schema_version":"1.0","canonical_sha256":"04b78fc311c408bef66fe9150c2da400d3f88ec902975b4f40f3f0a8ab83b841","source":{"kind":"arxiv","id":"2205.01500","version":2},"attestation_state":"computed","paper":{"title":"Meta Learning for Natural Language Processing: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Ngoc Thang Vu, Shang-Wen Li","submitted_at":"2022-05-03T13:58:38Z","abstract_excerpt":"Deep learning has been the mainstream technique in natural language processing (NLP) area. However, the techniques require many labeled data and are less generalizable across domains. Meta-learning is an arising field in machine learning studying approaches to learn better learning algorithms. Approaches aim at improving algorithms in various aspects, including data efficiency and generalizability. Efficacy of approaches has been shown in many NLP tasks, but there is no systematic survey of these approaches in NLP, which hinders more researchers from joining the field. Our goal with this surve"},"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":"2205.01500","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-03T13:58:38Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ab584eea761fa0c31254ce4072cb7b477de66375330cbd7fd14f49c8a80d842a","abstract_canon_sha256":"d9b66c9bb9edd0c338e7ba716cc16812f1f7c830cbeffa1f3dc2541828c4d64c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:49.142233Z","signature_b64":"ziaWLFbePInP1Y1jssqeAvDUTv0nz/ufz9gGgRJ38VMX1I5S9DrJQBu1dci4pUUuAXuEOM/otQf94pUSl5OVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04b78fc311c408bef66fe9150c2da400d3f88ec902975b4f40f3f0a8ab83b841","last_reissued_at":"2026-07-05T04:36:49.141760Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:49.141760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta Learning for Natural Language Processing: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hung-yi Lee, Ngoc Thang Vu, Shang-Wen Li","submitted_at":"2022-05-03T13:58:38Z","abstract_excerpt":"Deep learning has been the mainstream technique in natural language processing (NLP) area. However, the techniques require many labeled data and are less generalizable across domains. Meta-learning is an arising field in machine learning studying approaches to learn better learning algorithms. Approaches aim at improving algorithms in various aspects, including data efficiency and generalizability. Efficacy of approaches has been shown in many NLP tasks, but there is no systematic survey of these approaches in NLP, which hinders more researchers from joining the field. Our goal with this surve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.01500","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.01500/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":"2205.01500","created_at":"2026-07-05T04:36:49.141820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.01500v2","created_at":"2026-07-05T04:36:49.141820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.01500","created_at":"2026-07-05T04:36:49.141820+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS3Y7QYRYQEL","created_at":"2026-07-05T04:36:49.141820+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS3Y7QYRYQEL55TP","created_at":"2026-07-05T04:36:49.141820+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS3Y7QYR","created_at":"2026-07-05T04:36:49.141820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.19837","citing_title":"Meta-Learning and Meta-Reinforcement Learning -- Tracing the Path towards DeepMind's Adaptive Agent","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD","json":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD.json","graph_json":"https://pith.science/api/pith-number/AS3Y7QYRYQEL55TP5EKQYLNEAD/graph.json","events_json":"https://pith.science/api/pith-number/AS3Y7QYRYQEL55TP5EKQYLNEAD/events.json","paper":"https://pith.science/paper/AS3Y7QYR"},"agent_actions":{"view_html":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD","download_json":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD.json","view_paper":"https://pith.science/paper/AS3Y7QYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.01500&json=true","fetch_graph":"https://pith.science/api/pith-number/AS3Y7QYRYQEL55TP5EKQYLNEAD/graph.json","fetch_events":"https://pith.science/api/pith-number/AS3Y7QYRYQEL55TP5EKQYLNEAD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD/action/storage_attestation","attest_author":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD/action/author_attestation","sign_citation":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD/action/citation_signature","submit_replication":"https://pith.science/pith/AS3Y7QYRYQEL55TP5EKQYLNEAD/action/replication_record"}},"created_at":"2026-07-05T04:36:49.141820+00:00","updated_at":"2026-07-05T04:36:49.141820+00:00"}