{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:D3KYU2THJL5SENLDOFPX37JZH3","short_pith_number":"pith:D3KYU2TH","schema_version":"1.0","canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","source":{"kind":"arxiv","id":"1905.12598","version":2},"attestation_state":"computed","paper":{"title":"Towards better substitution-based word sense induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asaf Amrami, Yoav Goldberg","submitted_at":"2019-05-29T17:20:11Z","abstract_excerpt":"Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses. Recent work obtain strong results by clustering lexical substitutes derived from pre-trained RNN language models (ELMo). Adapting the method to BERT improves the scores even further. We extend the previous method to support a dynamic rather than a fixed number of clusters as supported by other prominent methods, and propose a method for interpreting the resulting clusters by associating them with their most informative substitutes. We then perform extensive error analysis r"},"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":"1905.12598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-29T17:20:11Z","cross_cats_sorted":[],"title_canon_sha256":"29071dc8f3186f3965cb07c19d983f72776d56f41022c1f9ca36a8e19af19435","abstract_canon_sha256":"f3f8de9d89dee8bcead065330162890ded284848f0ac67f613e111ca14248b27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:37.343339Z","signature_b64":"DqmG312ed3fY5fpAVo6fW0WD4qvkBY35gITLpoiGGmwGPDl77JEHBIOpYwIK/BuYydFzcQhQCeH8O/kf5uxlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed58a6a674afb223563715f7dfd393ee40f7cad8b1eeb595ffd2ccf03489009","last_reissued_at":"2026-05-17T23:44:37.342810Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:37.342810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards better substitution-based word sense induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Asaf Amrami, Yoav Goldberg","submitted_at":"2019-05-29T17:20:11Z","abstract_excerpt":"Word sense induction (WSI) is the task of unsupervised clustering of word usages within a sentence to distinguish senses. Recent work obtain strong results by clustering lexical substitutes derived from pre-trained RNN language models (ELMo). Adapting the method to BERT improves the scores even further. We extend the previous method to support a dynamic rather than a fixed number of clusters as supported by other prominent methods, and propose a method for interpreting the resulting clusters by associating them with their most informative substitutes. We then perform extensive error analysis r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12598","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":""},"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":"1905.12598","created_at":"2026-05-17T23:44:37.342896+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12598v2","created_at":"2026-05-17T23:44:37.342896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12598","created_at":"2026-05-17T23:44:37.342896+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3KYU2THJL5S","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3KYU2THJL5SENLD","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3KYU2TH","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.04497","citing_title":"Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3","json":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3.json","graph_json":"https://pith.science/api/pith-number/D3KYU2THJL5SENLDOFPX37JZH3/graph.json","events_json":"https://pith.science/api/pith-number/D3KYU2THJL5SENLDOFPX37JZH3/events.json","paper":"https://pith.science/paper/D3KYU2TH"},"agent_actions":{"view_html":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3","download_json":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3.json","view_paper":"https://pith.science/paper/D3KYU2TH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12598&json=true","fetch_graph":"https://pith.science/api/pith-number/D3KYU2THJL5SENLDOFPX37JZH3/graph.json","fetch_events":"https://pith.science/api/pith-number/D3KYU2THJL5SENLDOFPX37JZH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/action/storage_attestation","attest_author":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/action/author_attestation","sign_citation":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/action/citation_signature","submit_replication":"https://pith.science/pith/D3KYU2THJL5SENLDOFPX37JZH3/action/replication_record"}},"created_at":"2026-05-17T23:44:37.342896+00:00","updated_at":"2026-05-17T23:44:37.342896+00:00"}