{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:FUECVDTUMHWEDPYUPTLQZ4FGBH","short_pith_number":"pith:FUECVDTU","schema_version":"1.0","canonical_sha256":"2d082a8e7461ec41bf147cd70cf0a609d79e2a127397b4e374ecbccc9114f611","source":{"kind":"arxiv","id":"1907.00409","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charibeth Cheng, Jan Christian Blaise Cruz","submitted_at":"2019-06-30T16:32:28Z","abstract_excerpt":"Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly. In this paper, we alleviate this scarcity problem for the low-resourced Filipino language in two ways. First, we introduce a new benchmark language modeling dataset in Filipino which we call WikiText-TL-39. Second, we show that language model finetuning techniques such as BERT and ULMFiT can be used to consistently train robust classifiers in low-resource settings, experienc"},"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":"1907.00409","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-30T16:32:28Z","cross_cats_sorted":[],"title_canon_sha256":"e3a5bd3220949c8f329b8aaa4ca7b01c93d77731d8e9d99c61c2999933067b6b","abstract_canon_sha256":"bf1e5e3f7e8c55d838b2d94cac220ef14f6310b41a788c80e200e65e136ad2a0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:36.090060Z","signature_b64":"rwlSp1+ivvuH+6WYOWm6hfwWXiIISoAlrRTPUn/49M0Ur8uUfCN7CGV4aCAcgUEWOrsVyeLgSVv+nNLW4uCwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d082a8e7461ec41bf147cd70cf0a609d79e2a127397b4e374ecbccc9114f611","last_reissued_at":"2026-05-17T23:41:36.089278Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:36.089278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Language Model Finetuning Techniques for Low-resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Charibeth Cheng, Jan Christian Blaise Cruz","submitted_at":"2019-06-30T16:32:28Z","abstract_excerpt":"Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly. In this paper, we alleviate this scarcity problem for the low-resourced Filipino language in two ways. First, we introduce a new benchmark language modeling dataset in Filipino which we call WikiText-TL-39. Second, we show that language model finetuning techniques such as BERT and ULMFiT can be used to consistently train robust classifiers in low-resource settings, experienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.00409","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":""},"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":"1907.00409","created_at":"2026-05-17T23:41:36.089422+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.00409v1","created_at":"2026-05-17T23:41:36.089422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.00409","created_at":"2026-05-17T23:41:36.089422+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUECVDTUMHWE","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUECVDTUMHWEDPYU","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUECVDTU","created_at":"2026-05-18T12:33:15.570797+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/FUECVDTUMHWEDPYUPTLQZ4FGBH","json":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH.json","graph_json":"https://pith.science/api/pith-number/FUECVDTUMHWEDPYUPTLQZ4FGBH/graph.json","events_json":"https://pith.science/api/pith-number/FUECVDTUMHWEDPYUPTLQZ4FGBH/events.json","paper":"https://pith.science/paper/FUECVDTU"},"agent_actions":{"view_html":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH","download_json":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH.json","view_paper":"https://pith.science/paper/FUECVDTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.00409&json=true","fetch_graph":"https://pith.science/api/pith-number/FUECVDTUMHWEDPYUPTLQZ4FGBH/graph.json","fetch_events":"https://pith.science/api/pith-number/FUECVDTUMHWEDPYUPTLQZ4FGBH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH/action/storage_attestation","attest_author":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH/action/author_attestation","sign_citation":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH/action/citation_signature","submit_replication":"https://pith.science/pith/FUECVDTUMHWEDPYUPTLQZ4FGBH/action/replication_record"}},"created_at":"2026-05-17T23:41:36.089422+00:00","updated_at":"2026-05-17T23:41:36.089422+00:00"}