{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VJZW2XPMY3J5CZYXRDKLBKT4DK","short_pith_number":"pith:VJZW2XPM","schema_version":"1.0","canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","source":{"kind":"arxiv","id":"2409.20467","version":1},"attestation_state":"computed","paper":{"title":"A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anh Thi Hoang Nguyen, Dung Ha Nguyen, Kiet Van Nguyen","submitted_at":"2024-09-30T16:26:40Z","abstract_excerpt":"This study introduces an innovative automatic labeling framework to address the challenges of lexical normalization in social media texts for low-resource languages like Vietnamese. Social media data is rich and diverse, but the evolving and varied language used in these contexts makes manual labeling labor-intensive and expensive. To tackle these issues, we propose a framework that integrates semi-supervised learning with weak supervision techniques. This approach enhances the quality of training dataset and expands its size while minimizing manual labeling efforts. Our framework automaticall"},"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":"2409.20467","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-30T16:26:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"851bed48798e049ec5f1c9f6622ec9dbc6b09be5c01266932078a091304bb538","abstract_canon_sha256":"a4c14f9ec5e3b4554572246afbc68da8a79f94a8eacdf053e23e2195b59373f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:43.977333Z","signature_b64":"I9gCwhddnPCLaAQ/CjVi+090NJ9fD3l3hoK31ta2IXdnw1RsY22Xy4wTJ+vbbwTBbiBwsV202F2nrHMSrm+KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa736d5decc6d3d1671788d4b0aa7c1abed9819aef72c7c2fc888c887c8630a8","last_reissued_at":"2026-07-05T09:13:43.976783Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:43.976783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Weakly Supervised Data Labeling Framework for Machine Lexical Normalization in Vietnamese Social Media","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anh Thi Hoang Nguyen, Dung Ha Nguyen, Kiet Van Nguyen","submitted_at":"2024-09-30T16:26:40Z","abstract_excerpt":"This study introduces an innovative automatic labeling framework to address the challenges of lexical normalization in social media texts for low-resource languages like Vietnamese. Social media data is rich and diverse, but the evolving and varied language used in these contexts makes manual labeling labor-intensive and expensive. To tackle these issues, we propose a framework that integrates semi-supervised learning with weak supervision techniques. This approach enhances the quality of training dataset and expands its size while minimizing manual labeling efforts. Our framework automaticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.20467","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/2409.20467/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":"2409.20467","created_at":"2026-07-05T09:13:43.976839+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.20467v1","created_at":"2026-07-05T09:13:43.976839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.20467","created_at":"2026-07-05T09:13:43.976839+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJZW2XPMY3J5","created_at":"2026-07-05T09:13:43.976839+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJZW2XPMY3J5CZYX","created_at":"2026-07-05T09:13:43.976839+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJZW2XPM","created_at":"2026-07-05T09:13:43.976839+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.07020","citing_title":"ViSoLex: An Open-Source Repository for Vietnamese Social Media Lexical Normalization","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK","json":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK.json","graph_json":"https://pith.science/api/pith-number/VJZW2XPMY3J5CZYXRDKLBKT4DK/graph.json","events_json":"https://pith.science/api/pith-number/VJZW2XPMY3J5CZYXRDKLBKT4DK/events.json","paper":"https://pith.science/paper/VJZW2XPM"},"agent_actions":{"view_html":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK","download_json":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK.json","view_paper":"https://pith.science/paper/VJZW2XPM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.20467&json=true","fetch_graph":"https://pith.science/api/pith-number/VJZW2XPMY3J5CZYXRDKLBKT4DK/graph.json","fetch_events":"https://pith.science/api/pith-number/VJZW2XPMY3J5CZYXRDKLBKT4DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/action/storage_attestation","attest_author":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/action/author_attestation","sign_citation":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/action/citation_signature","submit_replication":"https://pith.science/pith/VJZW2XPMY3J5CZYXRDKLBKT4DK/action/replication_record"}},"created_at":"2026-07-05T09:13:43.976839+00:00","updated_at":"2026-07-05T09:13:43.976839+00:00"}