{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:J3K3PBDVEYAU5RF64FIUMBKXCC","short_pith_number":"pith:J3K3PBDV","schema_version":"1.0","canonical_sha256":"4ed5b7847526014ec4bee1514605571090e99b9f2a4ebc7c4e686b9d1397646e","source":{"kind":"arxiv","id":"2106.03103","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qian-Wen Zhang, Ruifang Liu, Ximing Zhang, Yunbo Cao, Zhao Yan","submitted_at":"2021-06-06T12:26:14Z","abstract_excerpt":"In multi-label text classification (MLTC), each given document is associated with a set of correlated labels. To capture label correlations, previous classifier-chain and sequence-to-sequence models transform MLTC to a sequence prediction task. However, they tend to suffer from label order dependency, label combination over-fitting and error propagation problems. To address these problems, we introduce a novel approach with multi-task learning to enhance label correlation feedback. We first utilize a joint embedding (JE) mechanism to obtain the text and label representation simultaneously. In "},"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":"2106.03103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-06T12:26:14Z","cross_cats_sorted":[],"title_canon_sha256":"22e8501042c35ac645904be3b0cecb0b26e2baa1fb4ab157aff2dcac2573679c","abstract_canon_sha256":"6558f985b6b93f9ed8bdc677558ffea9546eab4c0a372d2999bb3a3239bbd343"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:33.846016Z","signature_b64":"1OgNuHZLhQNv0FGBUAQt1QKOmh3V8f+AOcTMQSy7vygNN5txw8cAo0Au4BUKRaJkokm0kcUyGDwEscWdnYL0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ed5b7847526014ec4bee1514605571090e99b9f2a4ebc7c4e686b9d1397646e","last_reissued_at":"2026-07-05T02:46:33.845546Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:33.845546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Qian-Wen Zhang, Ruifang Liu, Ximing Zhang, Yunbo Cao, Zhao Yan","submitted_at":"2021-06-06T12:26:14Z","abstract_excerpt":"In multi-label text classification (MLTC), each given document is associated with a set of correlated labels. To capture label correlations, previous classifier-chain and sequence-to-sequence models transform MLTC to a sequence prediction task. However, they tend to suffer from label order dependency, label combination over-fitting and error propagation problems. To address these problems, we introduce a novel approach with multi-task learning to enhance label correlation feedback. We first utilize a joint embedding (JE) mechanism to obtain the text and label representation simultaneously. In "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03103","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/2106.03103/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":"2106.03103","created_at":"2026-07-05T02:46:33.845602+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03103v1","created_at":"2026-07-05T02:46:33.845602+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03103","created_at":"2026-07-05T02:46:33.845602+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3K3PBDVEYAU","created_at":"2026-07-05T02:46:33.845602+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3K3PBDVEYAU5RF6","created_at":"2026-07-05T02:46:33.845602+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3K3PBDV","created_at":"2026-07-05T02:46:33.845602+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00671","citing_title":"Multi-Label Node Classification with Label Influence Propagation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC","json":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC.json","graph_json":"https://pith.science/api/pith-number/J3K3PBDVEYAU5RF64FIUMBKXCC/graph.json","events_json":"https://pith.science/api/pith-number/J3K3PBDVEYAU5RF64FIUMBKXCC/events.json","paper":"https://pith.science/paper/J3K3PBDV"},"agent_actions":{"view_html":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC","download_json":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC.json","view_paper":"https://pith.science/paper/J3K3PBDV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03103&json=true","fetch_graph":"https://pith.science/api/pith-number/J3K3PBDVEYAU5RF64FIUMBKXCC/graph.json","fetch_events":"https://pith.science/api/pith-number/J3K3PBDVEYAU5RF64FIUMBKXCC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC/action/storage_attestation","attest_author":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC/action/author_attestation","sign_citation":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC/action/citation_signature","submit_replication":"https://pith.science/pith/J3K3PBDVEYAU5RF64FIUMBKXCC/action/replication_record"}},"created_at":"2026-07-05T02:46:33.845602+00:00","updated_at":"2026-07-05T02:46:33.845602+00:00"}