{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:RSHEER2WWSQKISJAZ3NV53DAE2","short_pith_number":"pith:RSHEER2W","schema_version":"1.0","canonical_sha256":"8c8e424756b4a0a44920cedb5eec6026b93ff52912ee0dc74673f46b560ad762","source":{"kind":"arxiv","id":"2005.00318","version":1},"attestation_state":"computed","paper":{"title":"Can Multilingual Language Models Transfer to an Unseen Dialect? A Case Study on North African Arabizi","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Muller, Benoit Sagot, Djam\\'e Seddah","submitted_at":"2020-05-01T11:29:23Z","abstract_excerpt":"Building natural language processing systems for non standardized and low resource languages is a difficult challenge. The recent success of large-scale multilingual pretrained language models provides new modeling tools to tackle this. In this work, we study the ability of multilingual language models to process an unseen dialect. We take user generated North-African Arabic as our case study, a resource-poor dialectal variety of Arabic with frequent code-mixing with French and written in Arabizi, a non-standardized transliteration of Arabic to Latin script. Focusing on two tasks, part-of-spee"},"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":"2005.00318","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-05-01T11:29:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e9d1abf4dcc3f58242b3690e67c7c65c0a0d89482dcb59250e220750bd98933e","abstract_canon_sha256":"a12bda48c3d3d850f9207b30dc12de1d41f9cabf9d8d0bf8077f6be0ed91841b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:39.964210Z","signature_b64":"+sIsewctordIpY6WEsyVIVhSBbTpwMLOvXREXykj2OL9CJIPYtGK+yml/DVnamNghUX1KFc9lzDW1GQQSByIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8e424756b4a0a44920cedb5eec6026b93ff52912ee0dc74673f46b560ad762","last_reissued_at":"2026-07-05T00:59:39.963819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:39.963819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Multilingual Language Models Transfer to an Unseen Dialect? A Case Study on North African Arabizi","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Muller, Benoit Sagot, Djam\\'e Seddah","submitted_at":"2020-05-01T11:29:23Z","abstract_excerpt":"Building natural language processing systems for non standardized and low resource languages is a difficult challenge. The recent success of large-scale multilingual pretrained language models provides new modeling tools to tackle this. In this work, we study the ability of multilingual language models to process an unseen dialect. We take user generated North-African Arabic as our case study, a resource-poor dialectal variety of Arabic with frequent code-mixing with French and written in Arabizi, a non-standardized transliteration of Arabic to Latin script. Focusing on two tasks, part-of-spee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00318","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/2005.00318/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":"2005.00318","created_at":"2026-07-05T00:59:39.963883+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00318v1","created_at":"2026-07-05T00:59:39.963883+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00318","created_at":"2026-07-05T00:59:39.963883+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSHEER2WWSQK","created_at":"2026-07-05T00:59:39.963883+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSHEER2WWSQKISJA","created_at":"2026-07-05T00:59:39.963883+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSHEER2W","created_at":"2026-07-05T00:59:39.963883+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/RSHEER2WWSQKISJAZ3NV53DAE2","json":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2.json","graph_json":"https://pith.science/api/pith-number/RSHEER2WWSQKISJAZ3NV53DAE2/graph.json","events_json":"https://pith.science/api/pith-number/RSHEER2WWSQKISJAZ3NV53DAE2/events.json","paper":"https://pith.science/paper/RSHEER2W"},"agent_actions":{"view_html":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2","download_json":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2.json","view_paper":"https://pith.science/paper/RSHEER2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00318&json=true","fetch_graph":"https://pith.science/api/pith-number/RSHEER2WWSQKISJAZ3NV53DAE2/graph.json","fetch_events":"https://pith.science/api/pith-number/RSHEER2WWSQKISJAZ3NV53DAE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2/action/storage_attestation","attest_author":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2/action/author_attestation","sign_citation":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2/action/citation_signature","submit_replication":"https://pith.science/pith/RSHEER2WWSQKISJAZ3NV53DAE2/action/replication_record"}},"created_at":"2026-07-05T00:59:39.963883+00:00","updated_at":"2026-07-05T00:59:39.963883+00:00"}