{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:L3QHCFZEZBC5372J72XNAGEVAG","short_pith_number":"pith:L3QHCFZE","schema_version":"1.0","canonical_sha256":"5ee0711724c845ddff49feaed0189501821ca796aa097908052510d93c1acf45","source":{"kind":"arxiv","id":"1606.02689","version":1},"attestation_state":"computed","paper":{"title":"Continuously Learning Neural Dialogue Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Vandyke, Lina Rojas-Barahona, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","submitted_at":"2016-06-08T19:03:06Z","abstract_excerpt":"We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model's effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model's performance in both interactive set"},"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":"1606.02689","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-08T19:03:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e8c02e34448a833597a5cfd90ce612025883f67c86b46391e188d3c044dabc95","abstract_canon_sha256":"2e13ff5ad02fa2799130774f1045632c45d218e08939b5d12e92a95f18475236"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:40.853237Z","signature_b64":"9PPOE9JlHsRxJ1zIBb2R7/rCC1ZGnHWhp5OvYY0ChSdfid1mt2mmt6ieAZPjWg/aoAubLDgbnvo3hYlz9/jfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ee0711724c845ddff49feaed0189501821ca796aa097908052510d93c1acf45","last_reissued_at":"2026-05-18T01:12:40.852879Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:40.852879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuously Learning Neural Dialogue Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"David Vandyke, Lina Rojas-Barahona, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","submitted_at":"2016-06-08T19:03:06Z","abstract_excerpt":"We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model's effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model's performance in both interactive set"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02689","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":"1606.02689","created_at":"2026-05-18T01:12:40.852942+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.02689v1","created_at":"2026-05-18T01:12:40.852942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02689","created_at":"2026-05-18T01:12:40.852942+00:00"},{"alias_kind":"pith_short_12","alias_value":"L3QHCFZEZBC5","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_16","alias_value":"L3QHCFZEZBC5372J","created_at":"2026-05-18T12:30:29.479603+00:00"},{"alias_kind":"pith_short_8","alias_value":"L3QHCFZE","created_at":"2026-05-18T12:30:29.479603+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/L3QHCFZEZBC5372J72XNAGEVAG","json":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG.json","graph_json":"https://pith.science/api/pith-number/L3QHCFZEZBC5372J72XNAGEVAG/graph.json","events_json":"https://pith.science/api/pith-number/L3QHCFZEZBC5372J72XNAGEVAG/events.json","paper":"https://pith.science/paper/L3QHCFZE"},"agent_actions":{"view_html":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG","download_json":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG.json","view_paper":"https://pith.science/paper/L3QHCFZE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.02689&json=true","fetch_graph":"https://pith.science/api/pith-number/L3QHCFZEZBC5372J72XNAGEVAG/graph.json","fetch_events":"https://pith.science/api/pith-number/L3QHCFZEZBC5372J72XNAGEVAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG/action/storage_attestation","attest_author":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG/action/author_attestation","sign_citation":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG/action/citation_signature","submit_replication":"https://pith.science/pith/L3QHCFZEZBC5372J72XNAGEVAG/action/replication_record"}},"created_at":"2026-05-18T01:12:40.852942+00:00","updated_at":"2026-05-18T01:12:40.852942+00:00"}