{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A7UECN4IHFXCZZVOJCPLZSBGOV","short_pith_number":"pith:A7UECN4I","schema_version":"1.0","canonical_sha256":"07e8413788396e2ce6ae489ebcc826757cc2b08c9bc9ee197966fbbd3e1f6ed6","source":{"kind":"arxiv","id":"1810.10254","version":2},"attestation_state":"computed","paper":{"title":"Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Genta Indra Winata, Pascale Fung","submitted_at":"2018-10-24T09:02:17Z","abstract_excerpt":"Building large-scale datasets for training code-switching language models is challenging and very expensive. To alleviate this problem using parallel corpus has been a major workaround. However, existing solutions use linguistic constraints which may not capture the real data distribution. In this work, we propose a novel method for learning how to generate code-switching sentences from parallel corpora. Our model uses a Seq2Seq model in combination with pointer networks to align and choose words from the monolingual sentences and form a grammatical code-switching sentence. In our experiment, "},"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":"1810.10254","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T09:02:17Z","cross_cats_sorted":[],"title_canon_sha256":"fadf40f33bee8b8b2f97631cd8eb4c0aa94c218dd2a716ecf9254eb1f483f88e","abstract_canon_sha256":"6fa640a904faa4e2636674d2e99025269ceaca00f8ffb8309bc9167a33564908"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:57.136459Z","signature_b64":"U/aJ5p04l5nErVAGoYFvahpfrEs+wPjvuDOCsXqJFMnUARRyhI6v/89knbWmnbD7Is7KiT8V755IOMu2MOQtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07e8413788396e2ce6ae489ebcc826757cc2b08c9bc9ee197966fbbd3e1f6ed6","last_reissued_at":"2026-05-18T00:01:57.135837Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:57.135837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Genta Indra Winata, Pascale Fung","submitted_at":"2018-10-24T09:02:17Z","abstract_excerpt":"Building large-scale datasets for training code-switching language models is challenging and very expensive. To alleviate this problem using parallel corpus has been a major workaround. However, existing solutions use linguistic constraints which may not capture the real data distribution. In this work, we propose a novel method for learning how to generate code-switching sentences from parallel corpora. Our model uses a Seq2Seq model in combination with pointer networks to align and choose words from the monolingual sentences and form a grammatical code-switching sentence. In our experiment, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10254","kind":"arxiv","version":2},"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":"1810.10254","created_at":"2026-05-18T00:01:57.135928+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.10254v2","created_at":"2026-05-18T00:01:57.135928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10254","created_at":"2026-05-18T00:01:57.135928+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7UECN4IHFXC","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7UECN4IHFXCZZVO","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7UECN4I","created_at":"2026-05-18T12:32:13.499390+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/A7UECN4IHFXCZZVOJCPLZSBGOV","json":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV.json","graph_json":"https://pith.science/api/pith-number/A7UECN4IHFXCZZVOJCPLZSBGOV/graph.json","events_json":"https://pith.science/api/pith-number/A7UECN4IHFXCZZVOJCPLZSBGOV/events.json","paper":"https://pith.science/paper/A7UECN4I"},"agent_actions":{"view_html":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV","download_json":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV.json","view_paper":"https://pith.science/paper/A7UECN4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.10254&json=true","fetch_graph":"https://pith.science/api/pith-number/A7UECN4IHFXCZZVOJCPLZSBGOV/graph.json","fetch_events":"https://pith.science/api/pith-number/A7UECN4IHFXCZZVOJCPLZSBGOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV/action/storage_attestation","attest_author":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV/action/author_attestation","sign_citation":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV/action/citation_signature","submit_replication":"https://pith.science/pith/A7UECN4IHFXCZZVOJCPLZSBGOV/action/replication_record"}},"created_at":"2026-05-18T00:01:57.135928+00:00","updated_at":"2026-05-18T00:01:57.135928+00:00"}