{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:G6DKB2LBVRLOHVO546A45TTZLF","short_pith_number":"pith:G6DKB2LB","schema_version":"1.0","canonical_sha256":"3786a0e961ac56e3d5dde781cece79596dd808f5cfc160937b9fce7b792df087","source":{"kind":"arxiv","id":"1911.11506","version":1},"attestation_state":"computed","paper":{"title":"Word-Class Embeddings for Multiclass Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Moreo, Andrea Esuli, Fabrizio Sebastiani","submitted_at":"2019-11-26T13:11:00Z","abstract_excerpt":"Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of this article) it seems appealing to enhance word representations with ad-hoc embeddings that encode task-specific information. We propose (supervised) word-class embeddings (WCEs), and show that, when concatenated to (unsupervised) pre-trained word embeddings, they substantially "},"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":"1911.11506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-26T13:11:00Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"88cb6ecc66f9c8410c078cb7d4bb433087448337bc5e83ceec3f3eda4485fb7b","abstract_canon_sha256":"4192ef26313bcd4cd2d16927accc5d5fbfbb2d91c14623371cded576080d6d60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:50.227043Z","signature_b64":"047l76ZGf+bwcfSVDt1F0NgTeFo2hG70v+RiCLzJc6v7JGWejiod69CCnvK7A7bQYmzLuo0GTT6EP0RLYurxCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3786a0e961ac56e3d5dde781cece79596dd808f5cfc160937b9fce7b792df087","last_reissued_at":"2026-07-05T03:15:50.226531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:50.226531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word-Class Embeddings for Multiclass Text Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alejandro Moreo, Andrea Esuli, Fabrizio Sebastiani","submitted_at":"2019-11-26T13:11:00Z","abstract_excerpt":"Pre-trained word embeddings encode general word semantics and lexical regularities of natural language, and have proven useful across many NLP tasks, including word sense disambiguation, machine translation, and sentiment analysis, to name a few. In supervised tasks such as multiclass text classification (the focus of this article) it seems appealing to enhance word representations with ad-hoc embeddings that encode task-specific information. We propose (supervised) word-class embeddings (WCEs), and show that, when concatenated to (unsupervised) pre-trained word embeddings, they substantially "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.11506","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/1911.11506/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":"1911.11506","created_at":"2026-07-05T03:15:50.226583+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.11506v1","created_at":"2026-07-05T03:15:50.226583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.11506","created_at":"2026-07-05T03:15:50.226583+00:00"},{"alias_kind":"pith_short_12","alias_value":"G6DKB2LBVRLO","created_at":"2026-07-05T03:15:50.226583+00:00"},{"alias_kind":"pith_short_16","alias_value":"G6DKB2LBVRLOHVO5","created_at":"2026-07-05T03:15:50.226583+00:00"},{"alias_kind":"pith_short_8","alias_value":"G6DKB2LB","created_at":"2026-07-05T03:15:50.226583+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/G6DKB2LBVRLOHVO546A45TTZLF","json":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF.json","graph_json":"https://pith.science/api/pith-number/G6DKB2LBVRLOHVO546A45TTZLF/graph.json","events_json":"https://pith.science/api/pith-number/G6DKB2LBVRLOHVO546A45TTZLF/events.json","paper":"https://pith.science/paper/G6DKB2LB"},"agent_actions":{"view_html":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF","download_json":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF.json","view_paper":"https://pith.science/paper/G6DKB2LB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.11506&json=true","fetch_graph":"https://pith.science/api/pith-number/G6DKB2LBVRLOHVO546A45TTZLF/graph.json","fetch_events":"https://pith.science/api/pith-number/G6DKB2LBVRLOHVO546A45TTZLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF/action/storage_attestation","attest_author":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF/action/author_attestation","sign_citation":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF/action/citation_signature","submit_replication":"https://pith.science/pith/G6DKB2LBVRLOHVO546A45TTZLF/action/replication_record"}},"created_at":"2026-07-05T03:15:50.226583+00:00","updated_at":"2026-07-05T03:15:50.226583+00:00"}