{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Y42IYCUKJUMENYB2MNMJFSYJ47","short_pith_number":"pith:Y42IYCUK","schema_version":"1.0","canonical_sha256":"c7348c0a8a4d1846e03a635892cb09e7c93e494e57697fb577db4477fc0ef5d9","source":{"kind":"arxiv","id":"1811.06031","version":2},"attestation_state":"computed","paper":{"title":"A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sebastian Ruder, Thomas Wolf, Victor Sanh","submitted_at":"2018-11-14T19:42:03Z","abstract_excerpt":"Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of understanding of the settings in which multi-task learning has a significant effect. In this work, we introduce a hierarchical model trained in a multi-task learning setup on a set of carefully selected semantic tasks. The model is trained in a hierarchical fashion to introduce an inductive bias by supervising a set of low level tasks at the bottom layers of 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":"1811.06031","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T19:42:03Z","cross_cats_sorted":[],"title_canon_sha256":"8567ac358f9ffc52e982ed7d7d067428bb088835901e38d55eff525f01bd5afc","abstract_canon_sha256":"e775266f8cd0eacc29c71b8467825531ad31956b82163f23c311122d96bdb572"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:57.415375Z","signature_b64":"UOIv7LfK877pxdRrOJ+OnV2aBadrTij9r20A3W6R3T4ZcvFkj6GKF4TLaTdPAdp8rfaU40jSnr9WIRozEoWABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7348c0a8a4d1846e03a635892cb09e7c93e494e57697fb577db4477fc0ef5d9","last_reissued_at":"2026-05-17T23:59:57.414927Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:57.414927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sebastian Ruder, Thomas Wolf, Victor Sanh","submitted_at":"2018-11-14T19:42:03Z","abstract_excerpt":"Much effort has been devoted to evaluate whether multi-task learning can be leveraged to learn rich representations that can be used in various Natural Language Processing (NLP) down-stream applications. However, there is still a lack of understanding of the settings in which multi-task learning has a significant effect. In this work, we introduce a hierarchical model trained in a multi-task learning setup on a set of carefully selected semantic tasks. The model is trained in a hierarchical fashion to introduce an inductive bias by supervising a set of low level tasks at the bottom layers of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.06031","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":"1811.06031","created_at":"2026-05-17T23:59:57.414989+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.06031v2","created_at":"2026-05-17T23:59:57.414989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.06031","created_at":"2026-05-17T23:59:57.414989+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y42IYCUKJUME","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y42IYCUKJUMENYB2","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y42IYCUK","created_at":"2026-05-18T12:33:04.347982+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/Y42IYCUKJUMENYB2MNMJFSYJ47","json":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47.json","graph_json":"https://pith.science/api/pith-number/Y42IYCUKJUMENYB2MNMJFSYJ47/graph.json","events_json":"https://pith.science/api/pith-number/Y42IYCUKJUMENYB2MNMJFSYJ47/events.json","paper":"https://pith.science/paper/Y42IYCUK"},"agent_actions":{"view_html":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47","download_json":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47.json","view_paper":"https://pith.science/paper/Y42IYCUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.06031&json=true","fetch_graph":"https://pith.science/api/pith-number/Y42IYCUKJUMENYB2MNMJFSYJ47/graph.json","fetch_events":"https://pith.science/api/pith-number/Y42IYCUKJUMENYB2MNMJFSYJ47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47/action/storage_attestation","attest_author":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47/action/author_attestation","sign_citation":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47/action/citation_signature","submit_replication":"https://pith.science/pith/Y42IYCUKJUMENYB2MNMJFSYJ47/action/replication_record"}},"created_at":"2026-05-17T23:59:57.414989+00:00","updated_at":"2026-05-17T23:59:57.414989+00:00"}