{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7TSMXQ2PE6TYES6KYLSXU37263","short_pith_number":"pith:7TSMXQ2P","schema_version":"1.0","canonical_sha256":"fce4cbc34f27a7824bcac2e57a6ffaf6d101a4c0e0b7c12432a8b6d863fe74b1","source":{"kind":"arxiv","id":"2210.10343","version":2},"attestation_state":"computed","paper":{"title":"Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aiwei Liu, Fei Huang, Lijie Wen, Pengjun Xie, Philip S. Yu, Xuming Hu, Yong Jiang, Zhongqiang Huang","submitted_at":"2022-10-19T07:24:40Z","abstract_excerpt":"Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks). Existing augmentation techniques either manipulate the words in the original text that break the semantic coherence of the text, or exploit generative models that ignore preserving entities in the original text, which impedes the use of augmentation techniques on nested and discontinuous NER tasks. In this work, we propose a novel Entity-to-Text based data augmentation technique named EnTDA to add, delete, replace or swap entities in the "},"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":"2210.10343","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T07:24:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eee1deee6610468bd486dbd5cd14e1836fb4ba8b69bfa69fed46e67042f93729","abstract_canon_sha256":"37e00686ab88b137b04175209edebdd927bbbf643519eb3678b9a027d0d8d117"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:05.821094Z","signature_b64":"0MpaEzhFY1HgYIgtBsk18zdwZbLJez3iMZPeOuGw44jWfv+SvURpxlmAtOnVwKeiPwqKO9BWrsBoG+ooML6MDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fce4cbc34f27a7824bcac2e57a6ffaf6d101a4c0e0b7c12432a8b6d863fe74b1","last_reissued_at":"2026-07-05T06:14:05.820704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:05.820704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entity-to-Text based Data Augmentation for various Named Entity Recognition Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aiwei Liu, Fei Huang, Lijie Wen, Pengjun Xie, Philip S. Yu, Xuming Hu, Yong Jiang, Zhongqiang Huang","submitted_at":"2022-10-19T07:24:40Z","abstract_excerpt":"Data augmentation techniques have been used to alleviate the problem of scarce labeled data in various NER tasks (flat, nested, and discontinuous NER tasks). Existing augmentation techniques either manipulate the words in the original text that break the semantic coherence of the text, or exploit generative models that ignore preserving entities in the original text, which impedes the use of augmentation techniques on nested and discontinuous NER tasks. In this work, we propose a novel Entity-to-Text based data augmentation technique named EnTDA to add, delete, replace or swap entities in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10343","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.10343/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":"2210.10343","created_at":"2026-07-05T06:14:05.820760+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.10343v2","created_at":"2026-07-05T06:14:05.820760+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10343","created_at":"2026-07-05T06:14:05.820760+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TSMXQ2PE6TY","created_at":"2026-07-05T06:14:05.820760+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TSMXQ2PE6TYES6K","created_at":"2026-07-05T06:14:05.820760+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TSMXQ2P","created_at":"2026-07-05T06:14:05.820760+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/7TSMXQ2PE6TYES6KYLSXU37263","json":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263.json","graph_json":"https://pith.science/api/pith-number/7TSMXQ2PE6TYES6KYLSXU37263/graph.json","events_json":"https://pith.science/api/pith-number/7TSMXQ2PE6TYES6KYLSXU37263/events.json","paper":"https://pith.science/paper/7TSMXQ2P"},"agent_actions":{"view_html":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263","download_json":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263.json","view_paper":"https://pith.science/paper/7TSMXQ2P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.10343&json=true","fetch_graph":"https://pith.science/api/pith-number/7TSMXQ2PE6TYES6KYLSXU37263/graph.json","fetch_events":"https://pith.science/api/pith-number/7TSMXQ2PE6TYES6KYLSXU37263/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263/action/storage_attestation","attest_author":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263/action/author_attestation","sign_citation":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263/action/citation_signature","submit_replication":"https://pith.science/pith/7TSMXQ2PE6TYES6KYLSXU37263/action/replication_record"}},"created_at":"2026-07-05T06:14:05.820760+00:00","updated_at":"2026-07-05T06:14:05.820760+00:00"}