{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:CHIZYBFICH7GVRFXL74RP74OJX","short_pith_number":"pith:CHIZYBFI","schema_version":"1.0","canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","source":{"kind":"arxiv","id":"1809.01962","version":1},"attestation_state":"computed","paper":{"title":"Code-switched Language Models Using Dual RNNs and Same-Source Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Preethi Jyothi, Saurabh Garg, Tanmay Parekh","submitted_at":"2018-09-06T13:12:27Z","abstract_excerpt":"This work focuses on building language models (LMs) for code-switched text. We propose two techniques that significantly improve these LMs: 1) A novel recurrent neural network unit with dual components that focus on each language in the code-switched text separately 2) Pretraining the LM using synthetic text from a generative model estimated using the training data. We demonstrate the effectiveness of our proposed techniques by reporting perplexities on a Mandarin-English task and derive significant reductions in perplexity."},"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":"1809.01962","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2018-09-06T13:12:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de88f4430d78ca5e009ba8d92f7d2e499ef696e625e2c7bc712fa1cdfafb9744","abstract_canon_sha256":"f3c510451e7e5bb901606b6abbec65f3a4cb9fce008b746b3021c2b28f17907e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:21.604957Z","signature_b64":"fHK21lWG5Zi7IvDt8ucTx11S2XekzWKjW7XuT+zQ1PXS9PHfXwGjtCgnT6T3MR2WTmbbhO1g4utTP/RV5fGTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11d19c04a811fe6ac4b75ff917ff8e4deb991fc431f9850f603c45428082f5bb","last_reissued_at":"2026-05-18T00:06:21.604545Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:21.604545Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code-switched Language Models Using Dual RNNs and Same-Source Pretraining","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Preethi Jyothi, Saurabh Garg, Tanmay Parekh","submitted_at":"2018-09-06T13:12:27Z","abstract_excerpt":"This work focuses on building language models (LMs) for code-switched text. We propose two techniques that significantly improve these LMs: 1) A novel recurrent neural network unit with dual components that focus on each language in the code-switched text separately 2) Pretraining the LM using synthetic text from a generative model estimated using the training data. We demonstrate the effectiveness of our proposed techniques by reporting perplexities on a Mandarin-English task and derive significant reductions in perplexity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01962","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":"1809.01962","created_at":"2026-05-18T00:06:21.604608+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.01962v1","created_at":"2026-05-18T00:06:21.604608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01962","created_at":"2026-05-18T00:06:21.604608+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHIZYBFICH7G","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHIZYBFICH7GVRFX","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHIZYBFI","created_at":"2026-05-18T12:32:16.446611+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08972","citing_title":"A Deep Generative Model for Code-Switched Text","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX","json":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX.json","graph_json":"https://pith.science/api/pith-number/CHIZYBFICH7GVRFXL74RP74OJX/graph.json","events_json":"https://pith.science/api/pith-number/CHIZYBFICH7GVRFXL74RP74OJX/events.json","paper":"https://pith.science/paper/CHIZYBFI"},"agent_actions":{"view_html":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX","download_json":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX.json","view_paper":"https://pith.science/paper/CHIZYBFI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.01962&json=true","fetch_graph":"https://pith.science/api/pith-number/CHIZYBFICH7GVRFXL74RP74OJX/graph.json","fetch_events":"https://pith.science/api/pith-number/CHIZYBFICH7GVRFXL74RP74OJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/action/storage_attestation","attest_author":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/action/author_attestation","sign_citation":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/action/citation_signature","submit_replication":"https://pith.science/pith/CHIZYBFICH7GVRFXL74RP74OJX/action/replication_record"}},"created_at":"2026-05-18T00:06:21.604608+00:00","updated_at":"2026-05-18T00:06:21.604608+00:00"}