{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RDYOSPRIWJAW5PPUQ6ADRNTYVM","short_pith_number":"pith:RDYOSPRI","schema_version":"1.0","canonical_sha256":"88f0e93e28b2416ebdf4878038b678ab2ea4e816035a1174bfab12469bd9d98c","source":{"kind":"arxiv","id":"2011.01549","version":1},"attestation_state":"computed","paper":{"title":"DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Canasai Kruengkrai, Chunyan Miao, Lidong Bing, Linlin Liu, Luo Si, Shafiq Joty, Thien Hai Nguyen","submitted_at":"2020-11-03T07:49:15Z","abstract_excerpt":"Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tas"},"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":"2011.01549","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T07:49:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f804a72558fed84f1d685a4ea6cfd2f1d68d9288601abdfb11b29738147b126a","abstract_canon_sha256":"3d58d8cc7dc7b027b316fc2ba36c98a6079b65b36b908881f17c0f3a9a5f0352"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:33.902591Z","signature_b64":"P9TWMrb78Yr6kK/d9PSn4gIXwHR4CtG1Ql/hN4V9HL5POQJNNgsm4xF707p8K2HZsOaCTqEQoAx2N7R35zfCAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88f0e93e28b2416ebdf4878038b678ab2ea4e816035a1174bfab12469bd9d98c","last_reissued_at":"2026-07-05T01:48:33.902239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:33.902239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bosheng Ding, Canasai Kruengkrai, Chunyan Miao, Lidong Bing, Linlin Liu, Luo Si, Shafiq Joty, Thien Hai Nguyen","submitted_at":"2020-11-03T07:49:15Z","abstract_excerpt":"Data augmentation techniques have been widely used to improve machine learning performance as they enhance the generalization capability of models. In this work, to generate high quality synthetic data for low-resource tagging tasks, we propose a novel augmentation method with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01549","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/2011.01549/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":"2011.01549","created_at":"2026-07-05T01:48:33.902299+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01549v1","created_at":"2026-07-05T01:48:33.902299+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01549","created_at":"2026-07-05T01:48:33.902299+00:00"},{"alias_kind":"pith_short_12","alias_value":"RDYOSPRIWJAW","created_at":"2026-07-05T01:48:33.902299+00:00"},{"alias_kind":"pith_short_16","alias_value":"RDYOSPRIWJAW5PPU","created_at":"2026-07-05T01:48:33.902299+00:00"},{"alias_kind":"pith_short_8","alias_value":"RDYOSPRI","created_at":"2026-07-05T01:48:33.902299+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/RDYOSPRIWJAW5PPUQ6ADRNTYVM","json":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM.json","graph_json":"https://pith.science/api/pith-number/RDYOSPRIWJAW5PPUQ6ADRNTYVM/graph.json","events_json":"https://pith.science/api/pith-number/RDYOSPRIWJAW5PPUQ6ADRNTYVM/events.json","paper":"https://pith.science/paper/RDYOSPRI"},"agent_actions":{"view_html":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM","download_json":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM.json","view_paper":"https://pith.science/paper/RDYOSPRI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01549&json=true","fetch_graph":"https://pith.science/api/pith-number/RDYOSPRIWJAW5PPUQ6ADRNTYVM/graph.json","fetch_events":"https://pith.science/api/pith-number/RDYOSPRIWJAW5PPUQ6ADRNTYVM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM/action/storage_attestation","attest_author":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM/action/author_attestation","sign_citation":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM/action/citation_signature","submit_replication":"https://pith.science/pith/RDYOSPRIWJAW5PPUQ6ADRNTYVM/action/replication_record"}},"created_at":"2026-07-05T01:48:33.902299+00:00","updated_at":"2026-07-05T01:48:33.902299+00:00"}