{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A7UECN4IHFXCZZVOJCPLZSBGOV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6fa640a904faa4e2636674d2e99025269ceaca00f8ffb8309bc9167a33564908","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T09:02:17Z","title_canon_sha256":"fadf40f33bee8b8b2f97631cd8eb4c0aa94c218dd2a716ecf9254eb1f483f88e"},"schema_version":"1.0","source":{"id":"1810.10254","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.10254","created_at":"2026-05-18T00:01:57Z"},{"alias_kind":"arxiv_version","alias_value":"1810.10254v2","created_at":"2026-05-18T00:01:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.10254","created_at":"2026-05-18T00:01:57Z"},{"alias_kind":"pith_short_12","alias_value":"A7UECN4IHFXC","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A7UECN4IHFXCZZVO","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A7UECN4I","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:e1d895ec199b104f684da9f8a566e50e0b08492f148b820fd935ed6238530864","target":"graph","created_at":"2026-05-18T00:01:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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, ","authors_text":"Andrea Madotto, Chien-Sheng Wu, Genta Indra Winata, Pascale Fung","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T09:02:17Z","title":"Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.10254","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2dd0d0ad38632e4460f1d0b58c88e591546ab10fdd575f1992dd01c448519601","target":"record","created_at":"2026-05-18T00:01:57Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6fa640a904faa4e2636674d2e99025269ceaca00f8ffb8309bc9167a33564908","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-10-24T09:02:17Z","title_canon_sha256":"fadf40f33bee8b8b2f97631cd8eb4c0aa94c218dd2a716ecf9254eb1f483f88e"},"schema_version":"1.0","source":{"id":"1810.10254","kind":"arxiv","version":2}},"canonical_sha256":"07e8413788396e2ce6ae489ebcc826757cc2b08c9bc9ee197966fbbd3e1f6ed6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07e8413788396e2ce6ae489ebcc826757cc2b08c9bc9ee197966fbbd3e1f6ed6","first_computed_at":"2026-05-18T00:01:57.135837Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:57.135837Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U/aJ5p04l5nErVAGoYFvahpfrEs+wPjvuDOCsXqJFMnUARRyhI6v/89knbWmnbD7Is7KiT8V755IOMu2MOQtDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:57.136459Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.10254","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2dd0d0ad38632e4460f1d0b58c88e591546ab10fdd575f1992dd01c448519601","sha256:e1d895ec199b104f684da9f8a566e50e0b08492f148b820fd935ed6238530864"],"state_sha256":"ca7a4df37bcc9e7838a5e54a2011a29fdf973b1db4e204c8a540b150154e58f7"}