{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IG5VLLHKZIZAQ64BCC5EUFX2HH","short_pith_number":"pith:IG5VLLHK","schema_version":"1.0","canonical_sha256":"41bb55aceaca32087b8110ba4a16fa39e8347cfaae700bf6a6cfd58cbf042def","source":{"kind":"arxiv","id":"2106.02960","version":1},"attestation_state":"computed","paper":{"title":"Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cees G.M. Snoek, Ekaterina Shutova, Nithin Holla, Xiantong Zhen, Yingjun Du","submitted_at":"2021-06-05T20:40:01Z","abstract_excerpt":"A critical challenge faced by supervised word sense disambiguation (WSD) is the lack of large annotated datasets with sufficient coverage of words in their diversity of senses. This inspired recent research on few-shot WSD using meta-learning. While such work has successfully applied meta-learning to learn new word senses from very few examples, its performance still lags behind its fully supervised counterpart. Aiming to further close this gap, we propose a model of semantic memory for WSD in a meta-learning setting. Semantic memory encapsulates prior experiences seen throughout the lifetime "},"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":"2106.02960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-05T20:40:01Z","cross_cats_sorted":[],"title_canon_sha256":"f9437fcc39fb22a7532a8cd6a58f3093fdc89791b504ce04f5797f5093fd3d4d","abstract_canon_sha256":"41acceb9faef4dd2091142e192ef45213b98559407f883ce13b604edfe4be37f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:32.212050Z","signature_b64":"sbcLMFsiF+C/dWtaGjxkAE/Rxy9MhxjHuO8x4FSkc5TyzonCSUxCqfs5fDlLOvjoH1bwYHkULDLJ1ewQVERDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41bb55aceaca32087b8110ba4a16fa39e8347cfaae700bf6a6cfd58cbf042def","last_reissued_at":"2026-07-05T02:46:32.211659Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:32.211659Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Learning with Variational Semantic Memory for Word Sense Disambiguation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cees G.M. Snoek, Ekaterina Shutova, Nithin Holla, Xiantong Zhen, Yingjun Du","submitted_at":"2021-06-05T20:40:01Z","abstract_excerpt":"A critical challenge faced by supervised word sense disambiguation (WSD) is the lack of large annotated datasets with sufficient coverage of words in their diversity of senses. This inspired recent research on few-shot WSD using meta-learning. While such work has successfully applied meta-learning to learn new word senses from very few examples, its performance still lags behind its fully supervised counterpart. Aiming to further close this gap, we propose a model of semantic memory for WSD in a meta-learning setting. Semantic memory encapsulates prior experiences seen throughout the lifetime "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02960","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/2106.02960/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":"2106.02960","created_at":"2026-07-05T02:46:32.211718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.02960v1","created_at":"2026-07-05T02:46:32.211718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02960","created_at":"2026-07-05T02:46:32.211718+00:00"},{"alias_kind":"pith_short_12","alias_value":"IG5VLLHKZIZA","created_at":"2026-07-05T02:46:32.211718+00:00"},{"alias_kind":"pith_short_16","alias_value":"IG5VLLHKZIZAQ64B","created_at":"2026-07-05T02:46:32.211718+00:00"},{"alias_kind":"pith_short_8","alias_value":"IG5VLLHK","created_at":"2026-07-05T02:46:32.211718+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/IG5VLLHKZIZAQ64BCC5EUFX2HH","json":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH.json","graph_json":"https://pith.science/api/pith-number/IG5VLLHKZIZAQ64BCC5EUFX2HH/graph.json","events_json":"https://pith.science/api/pith-number/IG5VLLHKZIZAQ64BCC5EUFX2HH/events.json","paper":"https://pith.science/paper/IG5VLLHK"},"agent_actions":{"view_html":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH","download_json":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH.json","view_paper":"https://pith.science/paper/IG5VLLHK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.02960&json=true","fetch_graph":"https://pith.science/api/pith-number/IG5VLLHKZIZAQ64BCC5EUFX2HH/graph.json","fetch_events":"https://pith.science/api/pith-number/IG5VLLHKZIZAQ64BCC5EUFX2HH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH/action/storage_attestation","attest_author":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH/action/author_attestation","sign_citation":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH/action/citation_signature","submit_replication":"https://pith.science/pith/IG5VLLHKZIZAQ64BCC5EUFX2HH/action/replication_record"}},"created_at":"2026-07-05T02:46:32.211718+00:00","updated_at":"2026-07-05T02:46:32.211718+00:00"}