{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:HMNLIHBXDZSBPNV26IGHTK3KVL","short_pith_number":"pith:HMNLIHBX","schema_version":"1.0","canonical_sha256":"3b1ab41c371e6417b6baf20c79ab6aaad431814763d808aab6784f242b891090","source":{"kind":"arxiv","id":"1812.04160","version":2},"attestation_state":"computed","paper":{"title":"Delta Embedding Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dejing Dou, Ji Wu, Xiao Zhang","submitted_at":"2018-12-11T00:19:32Z","abstract_excerpt":"Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better w"},"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":"1812.04160","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-11T00:19:32Z","cross_cats_sorted":[],"title_canon_sha256":"d10a4abcc1f60f61a2a3e38eb1ab86a1df33c8c37f63240461fd806055cffe40","abstract_canon_sha256":"4f4b1fcd84efd1cf3c7f1013a42584b1069347f18e9c0b99f9d592d124fce865"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:56.364385Z","signature_b64":"QS5VL5swNwjbT8wg3STMWly+1M8gPVKZy3gA7kdkNw7psFf870FZvo5XOB0xpuxbYQIloM5xGrIrfI+jFKxaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b1ab41c371e6417b6baf20c79ab6aaad431814763d808aab6784f242b891090","last_reissued_at":"2026-05-17T23:43:56.363674Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:56.363674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Delta Embedding Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dejing Dou, Ji Wu, Xiao Zhang","submitted_at":"2018-12-11T00:19:32Z","abstract_excerpt":"Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.04160","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":"1812.04160","created_at":"2026-05-17T23:43:56.363797+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.04160v2","created_at":"2026-05-17T23:43:56.363797+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.04160","created_at":"2026-05-17T23:43:56.363797+00:00"},{"alias_kind":"pith_short_12","alias_value":"HMNLIHBXDZSB","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"HMNLIHBXDZSBPNV2","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"HMNLIHBX","created_at":"2026-05-18T12:32:28.185984+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/HMNLIHBXDZSBPNV26IGHTK3KVL","json":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL.json","graph_json":"https://pith.science/api/pith-number/HMNLIHBXDZSBPNV26IGHTK3KVL/graph.json","events_json":"https://pith.science/api/pith-number/HMNLIHBXDZSBPNV26IGHTK3KVL/events.json","paper":"https://pith.science/paper/HMNLIHBX"},"agent_actions":{"view_html":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL","download_json":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL.json","view_paper":"https://pith.science/paper/HMNLIHBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.04160&json=true","fetch_graph":"https://pith.science/api/pith-number/HMNLIHBXDZSBPNV26IGHTK3KVL/graph.json","fetch_events":"https://pith.science/api/pith-number/HMNLIHBXDZSBPNV26IGHTK3KVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL/action/storage_attestation","attest_author":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL/action/author_attestation","sign_citation":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL/action/citation_signature","submit_replication":"https://pith.science/pith/HMNLIHBXDZSBPNV26IGHTK3KVL/action/replication_record"}},"created_at":"2026-05-17T23:43:56.363797+00:00","updated_at":"2026-05-17T23:43:56.363797+00:00"}