{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NP43E2VXUEWKO3DAFERBZADKWT","short_pith_number":"pith:NP43E2VX","schema_version":"1.0","canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","source":{"kind":"arxiv","id":"2504.08792","version":1},"attestation_state":"computed","paper":{"title":"Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Thamar Solorio, Toqeer Ehsan","submitted_at":"2025-04-07T15:18:34Z","abstract_excerpt":"Named Entity Recognition (NER), a fundamental task in Natural Language Processing (NLP), has shown significant advancements for high-resource languages. However, due to a lack of annotated datasets and limited representation in Pre-trained Language Models (PLMs), it remains understudied and challenging for low-resource languages. To address these challenges, we propose a data augmentation technique that generates culturally plausible sentences and experiments on four low-resource Pakistani languages; Urdu, Shahmukhi, Sindhi, and Pashto. By fine-tuning multilingual masked Large Language Models "},"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":"2504.08792","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-07T15:18:34Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"259aaf75bae7422554d5cacb40554d0e2fc52452f3cb70e2e1154c78157a8d1d","abstract_canon_sha256":"61139f79fa7c47556fb8471d90fac6db99993ffbae6bd9c4a8e8f64766a52449"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:59.382373Z","signature_b64":"/9rCuC66H34NlhPx4wEqrB/Y0pYUGBC0eQjFOPdoj5lwH3XZTGVQLPFo7wBXJQlaOjhhvelkVi/JkfZJKLOsCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bf9b26ab7a12ca76c6029221c806ab4f26462d98f123850766a99abeabe6e2f","last_reissued_at":"2026-07-05T10:47:59.381898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:59.381898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing NER Performance in Low-Resource Pakistani Languages using Cross-Lingual Data Augmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Thamar Solorio, Toqeer Ehsan","submitted_at":"2025-04-07T15:18:34Z","abstract_excerpt":"Named Entity Recognition (NER), a fundamental task in Natural Language Processing (NLP), has shown significant advancements for high-resource languages. However, due to a lack of annotated datasets and limited representation in Pre-trained Language Models (PLMs), it remains understudied and challenging for low-resource languages. To address these challenges, we propose a data augmentation technique that generates culturally plausible sentences and experiments on four low-resource Pakistani languages; Urdu, Shahmukhi, Sindhi, and Pashto. By fine-tuning multilingual masked Large Language Models "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08792","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/2504.08792/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":"2504.08792","created_at":"2026-07-05T10:47:59.381945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08792v1","created_at":"2026-07-05T10:47:59.381945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08792","created_at":"2026-07-05T10:47:59.381945+00:00"},{"alias_kind":"pith_short_12","alias_value":"NP43E2VXUEWK","created_at":"2026-07-05T10:47:59.381945+00:00"},{"alias_kind":"pith_short_16","alias_value":"NP43E2VXUEWKO3DA","created_at":"2026-07-05T10:47:59.381945+00:00"},{"alias_kind":"pith_short_8","alias_value":"NP43E2VX","created_at":"2026-07-05T10:47:59.381945+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/NP43E2VXUEWKO3DAFERBZADKWT","json":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT.json","graph_json":"https://pith.science/api/pith-number/NP43E2VXUEWKO3DAFERBZADKWT/graph.json","events_json":"https://pith.science/api/pith-number/NP43E2VXUEWKO3DAFERBZADKWT/events.json","paper":"https://pith.science/paper/NP43E2VX"},"agent_actions":{"view_html":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT","download_json":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT.json","view_paper":"https://pith.science/paper/NP43E2VX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08792&json=true","fetch_graph":"https://pith.science/api/pith-number/NP43E2VXUEWKO3DAFERBZADKWT/graph.json","fetch_events":"https://pith.science/api/pith-number/NP43E2VXUEWKO3DAFERBZADKWT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/action/storage_attestation","attest_author":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/action/author_attestation","sign_citation":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/action/citation_signature","submit_replication":"https://pith.science/pith/NP43E2VXUEWKO3DAFERBZADKWT/action/replication_record"}},"created_at":"2026-07-05T10:47:59.381945+00:00","updated_at":"2026-07-05T10:47:59.381945+00:00"}