{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IUCFAFIQRXE7I5WOD24AXZT6SP","short_pith_number":"pith:IUCFAFIQ","schema_version":"1.0","canonical_sha256":"45045015108dc9f476ce1eb80be67e93ee1ae2a94b1f61661b7a54ebe3c794f1","source":{"kind":"arxiv","id":"2001.11453","version":3},"attestation_state":"computed","paper":{"title":"Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Edoardo M. Ponti, Ivan Vuli\\'c, Marinela Parovic, Roi Reichart, Ryan Cotterell","submitted_at":"2020-01-30T16:58:56Z","abstract_excerpt":"Most combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task-language combinations with available data to low-resource ones? In this work, we propose a Bayesian generative model for the space of neural parameters. We assume that this space can be factorized into latent variables for each language and each task. We infer the posteriors over such latent variables based on data from seen task-language combinations through variational inference. T"},"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":"2001.11453","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-01-30T16:58:56Z","cross_cats_sorted":[],"title_canon_sha256":"ddb04b981e7266c045b5dbe1f7c24d16cf9ab2198b5404e4ddd288a5eae1dea7","abstract_canon_sha256":"34e8aa9ef1c6a42d0b9213e0d3ac295280603e5af1dda077bff7bcd6bd590d4b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:18.876596Z","signature_b64":"ZZYGSUmeI0l1i60F7ypml3nIHEh9CfQ9U4Fq3rqfpDBu+qJ2VwTTeX7HXpfjPclA7AZys6KF1CL/s7MdCDC5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45045015108dc9f476ce1eb80be67e93ee1ae2a94b1f61661b7a54ebe3c794f1","last_reissued_at":"2026-07-05T01:53:18.876188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:18.876188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parameter Space Factorization for Zero-Shot Learning across Tasks and Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anna Korhonen, Edoardo M. Ponti, Ivan Vuli\\'c, Marinela Parovic, Roi Reichart, Ryan Cotterell","submitted_at":"2020-01-30T16:58:56Z","abstract_excerpt":"Most combinations of NLP tasks and language varieties lack in-domain examples for supervised training because of the paucity of annotated data. How can neural models make sample-efficient generalizations from task-language combinations with available data to low-resource ones? In this work, we propose a Bayesian generative model for the space of neural parameters. We assume that this space can be factorized into latent variables for each language and each task. We infer the posteriors over such latent variables based on data from seen task-language combinations through variational inference. T"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.11453","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/2001.11453/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":"2001.11453","created_at":"2026-07-05T01:53:18.876244+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.11453v3","created_at":"2026-07-05T01:53:18.876244+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.11453","created_at":"2026-07-05T01:53:18.876244+00:00"},{"alias_kind":"pith_short_12","alias_value":"IUCFAFIQRXE7","created_at":"2026-07-05T01:53:18.876244+00:00"},{"alias_kind":"pith_short_16","alias_value":"IUCFAFIQRXE7I5WO","created_at":"2026-07-05T01:53:18.876244+00:00"},{"alias_kind":"pith_short_8","alias_value":"IUCFAFIQ","created_at":"2026-07-05T01:53:18.876244+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17715","citing_title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP","json":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP.json","graph_json":"https://pith.science/api/pith-number/IUCFAFIQRXE7I5WOD24AXZT6SP/graph.json","events_json":"https://pith.science/api/pith-number/IUCFAFIQRXE7I5WOD24AXZT6SP/events.json","paper":"https://pith.science/paper/IUCFAFIQ"},"agent_actions":{"view_html":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP","download_json":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP.json","view_paper":"https://pith.science/paper/IUCFAFIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.11453&json=true","fetch_graph":"https://pith.science/api/pith-number/IUCFAFIQRXE7I5WOD24AXZT6SP/graph.json","fetch_events":"https://pith.science/api/pith-number/IUCFAFIQRXE7I5WOD24AXZT6SP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP/action/storage_attestation","attest_author":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP/action/author_attestation","sign_citation":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP/action/citation_signature","submit_replication":"https://pith.science/pith/IUCFAFIQRXE7I5WOD24AXZT6SP/action/replication_record"}},"created_at":"2026-07-05T01:53:18.876244+00:00","updated_at":"2026-07-05T01:53:18.876244+00:00"}