{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V7JWJ7BCP4DIQFKX5FPCAALFOJ","short_pith_number":"pith:V7JWJ7BC","schema_version":"1.0","canonical_sha256":"afd364fc227f06881557e95e200165727613503e038fe2a0a716fe3cc5831442","source":{"kind":"arxiv","id":"1905.13359","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahad AlGhamdi, Mona Diab","submitted_at":"2019-05-31T00:08:27Z","abstract_excerpt":"Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given state-of-the-art monolingual NLP technologies since such technologies are geared toward the processing of one language at a time. In this paper, we address the problem of Part-of-Speech tagging (POS) in the context of linguistic code switching (CS). We explore leveraging multiple neural network architectures to measure the impact of different pre-trained em"},"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":"1905.13359","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-31T00:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"9bcf2418af363be0f685eecce4445e5a77f483894d010a87107a726386816800","abstract_canon_sha256":"cb22c13cc03d737047647af805013149b0b4eabaa83855761c9d45418b89d803"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:01.741258Z","signature_b64":"2axR3cRzUJ/p+0hjxnNhBXML8Tr+M5LDOnk7Yt3FqSwEkMONEBYCmF/tzdUc9Zl/mq5iI40WNrJ/0BiAa+m3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afd364fc227f06881557e95e200165727613503e038fe2a0a716fe3cc5831442","last_reissued_at":"2026-07-05T00:10:01.740846Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:01.740846Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Pretrained Word Embeddings for Part-of-Speech Tagging of Code Switching Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fahad AlGhamdi, Mona Diab","submitted_at":"2019-05-31T00:08:27Z","abstract_excerpt":"Linguistic Code Switching (CS) is a phenomenon that occurs when multilingual speakers alternate between two or more languages/dialects within a single conversation. Processing CS data is especially challenging in intra-sentential data given state-of-the-art monolingual NLP technologies since such technologies are geared toward the processing of one language at a time. In this paper, we address the problem of Part-of-Speech tagging (POS) in the context of linguistic code switching (CS). We explore leveraging multiple neural network architectures to measure the impact of different pre-trained em"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13359","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/1905.13359/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":"1905.13359","created_at":"2026-07-05T00:10:01.740901+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13359v1","created_at":"2026-07-05T00:10:01.740901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13359","created_at":"2026-07-05T00:10:01.740901+00:00"},{"alias_kind":"pith_short_12","alias_value":"V7JWJ7BCP4DI","created_at":"2026-07-05T00:10:01.740901+00:00"},{"alias_kind":"pith_short_16","alias_value":"V7JWJ7BCP4DIQFKX","created_at":"2026-07-05T00:10:01.740901+00:00"},{"alias_kind":"pith_short_8","alias_value":"V7JWJ7BC","created_at":"2026-07-05T00:10:01.740901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13419","citing_title":"A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directions","ref_index":2015,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ","json":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ.json","graph_json":"https://pith.science/api/pith-number/V7JWJ7BCP4DIQFKX5FPCAALFOJ/graph.json","events_json":"https://pith.science/api/pith-number/V7JWJ7BCP4DIQFKX5FPCAALFOJ/events.json","paper":"https://pith.science/paper/V7JWJ7BC"},"agent_actions":{"view_html":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ","download_json":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ.json","view_paper":"https://pith.science/paper/V7JWJ7BC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13359&json=true","fetch_graph":"https://pith.science/api/pith-number/V7JWJ7BCP4DIQFKX5FPCAALFOJ/graph.json","fetch_events":"https://pith.science/api/pith-number/V7JWJ7BCP4DIQFKX5FPCAALFOJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ/action/storage_attestation","attest_author":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ/action/author_attestation","sign_citation":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ/action/citation_signature","submit_replication":"https://pith.science/pith/V7JWJ7BCP4DIQFKX5FPCAALFOJ/action/replication_record"}},"created_at":"2026-07-05T00:10:01.740901+00:00","updated_at":"2026-07-05T00:10:01.740901+00:00"}