{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2NXQ5WZ7FXPDR7HBFWCOOEIUKD","short_pith_number":"pith:2NXQ5WZ7","schema_version":"1.0","canonical_sha256":"d36f0edb3f2dde38fce12d84e7111450f6d88c85d371aeda68918d0dc4652d26","source":{"kind":"arxiv","id":"1901.09296","version":1},"attestation_state":"computed","paper":{"title":"Variational Smoothing in Recurrent Neural Network Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Gabor Melis, Lei Yu, Lingpeng Kong, Wang Ling","submitted_at":"2019-01-27T00:46:27Z","abstract_excerpt":"We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017). We show that each variant of data noising is an instance of Bayesian recurrent neural networks with a particular variational distribution (i.e., a mixture of Gaussians whose weights depend on statistics derived from the corpus such as the unigram distribution). We use this insight to propose a more principled method to apply at prediction time and propose natural extensions to data noising under the variational framework. In particular, we propose variational smoothing with "},"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":"1901.09296","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-01-27T00:46:27Z","cross_cats_sorted":[],"title_canon_sha256":"a5e224f9c640af424582358563a33ea15f4b3233a62f0ca5e72b1b815b1b434c","abstract_canon_sha256":"5aae799d691f5b931d321efbbedb2c30a9db0ac455262408246ff92df22023e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:25.181541Z","signature_b64":"kmZojWpM7GARM9p5H4v6xsfmcWo9FOXcsew7RnRLfClu1EMHtqxS5L/+4QnzRlZldpf7IOb2Gj+iA1vul5nJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d36f0edb3f2dde38fce12d84e7111450f6d88c85d371aeda68918d0dc4652d26","last_reissued_at":"2026-05-17T23:55:25.180973Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:25.180973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Smoothing in Recurrent Neural Network Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dani Yogatama, Gabor Melis, Lei Yu, Lingpeng Kong, Wang Ling","submitted_at":"2019-01-27T00:46:27Z","abstract_excerpt":"We present a new theoretical perspective of data noising in recurrent neural network language models (Xie et al., 2017). We show that each variant of data noising is an instance of Bayesian recurrent neural networks with a particular variational distribution (i.e., a mixture of Gaussians whose weights depend on statistics derived from the corpus such as the unigram distribution). We use this insight to propose a more principled method to apply at prediction time and propose natural extensions to data noising under the variational framework. In particular, we propose variational smoothing with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09296","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":"1901.09296","created_at":"2026-05-17T23:55:25.181054+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.09296v1","created_at":"2026-05-17T23:55:25.181054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09296","created_at":"2026-05-17T23:55:25.181054+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NXQ5WZ7FXPD","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NXQ5WZ7FXPDR7HB","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NXQ5WZ7","created_at":"2026-05-18T12:33:07.085635+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/2NXQ5WZ7FXPDR7HBFWCOOEIUKD","json":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD.json","graph_json":"https://pith.science/api/pith-number/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/graph.json","events_json":"https://pith.science/api/pith-number/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/events.json","paper":"https://pith.science/paper/2NXQ5WZ7"},"agent_actions":{"view_html":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD","download_json":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD.json","view_paper":"https://pith.science/paper/2NXQ5WZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.09296&json=true","fetch_graph":"https://pith.science/api/pith-number/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/graph.json","fetch_events":"https://pith.science/api/pith-number/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/action/storage_attestation","attest_author":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/action/author_attestation","sign_citation":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/action/citation_signature","submit_replication":"https://pith.science/pith/2NXQ5WZ7FXPDR7HBFWCOOEIUKD/action/replication_record"}},"created_at":"2026-05-17T23:55:25.181054+00:00","updated_at":"2026-05-17T23:55:25.181054+00:00"}