{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WOFFQIQ43ZWSNQRYNGNG2J3OEX","short_pith_number":"pith:WOFFQIQ4","schema_version":"1.0","canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","source":{"kind":"arxiv","id":"1804.06512","version":1},"attestation_state":"computed","paper":{"title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Dilek Hakkani-Tur, Gokhan Tur, Larry Heck, Pararth Shah","submitted_at":"2018-04-18T00:26:38Z","abstract_excerpt":"In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction wi"},"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":"1804.06512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-18T00:26:38Z","cross_cats_sorted":[],"title_canon_sha256":"4da3fe595531c6cdb9b66b6d7e47d3b68e0b733151880483f7a7eae6b8f20819","abstract_canon_sha256":"ef0d24159034137799839cde7323b4cdb8ae904a90d0c1f095c2893d65ac2392"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:06.424084Z","signature_b64":"PVzQEEnZbVVZiKJ+ewfG9HO30xE6U6BWSAf+JVJ73P9G0E+vo+H1JNd/sS69AW7vNthzm60KbNQ5G8O1r/bNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b38a58221cde6d26c238699a6d276e25c91409627ead000c567e61e300464659","last_reissued_at":"2026-05-18T00:18:06.423524Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:06.423524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Dilek Hakkani-Tur, Gokhan Tur, Larry Heck, Pararth Shah","submitted_at":"2018-04-18T00:26:38Z","abstract_excerpt":"In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. Efficiency of such learning method may suffer from the mismatch of dialogue state distribution between offline training and online interactive learning stages. To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06512","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":"1804.06512","created_at":"2026-05-18T00:18:06.423634+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06512v1","created_at":"2026-05-18T00:18:06.423634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06512","created_at":"2026-05-18T00:18:06.423634+00:00"},{"alias_kind":"pith_short_12","alias_value":"WOFFQIQ43ZWS","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WOFFQIQ43ZWSNQRY","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WOFFQIQ4","created_at":"2026-05-18T12:33:01.666342+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/WOFFQIQ43ZWSNQRYNGNG2J3OEX","json":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX.json","graph_json":"https://pith.science/api/pith-number/WOFFQIQ43ZWSNQRYNGNG2J3OEX/graph.json","events_json":"https://pith.science/api/pith-number/WOFFQIQ43ZWSNQRYNGNG2J3OEX/events.json","paper":"https://pith.science/paper/WOFFQIQ4"},"agent_actions":{"view_html":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX","download_json":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX.json","view_paper":"https://pith.science/paper/WOFFQIQ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06512&json=true","fetch_graph":"https://pith.science/api/pith-number/WOFFQIQ43ZWSNQRYNGNG2J3OEX/graph.json","fetch_events":"https://pith.science/api/pith-number/WOFFQIQ43ZWSNQRYNGNG2J3OEX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/action/storage_attestation","attest_author":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/action/author_attestation","sign_citation":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/action/citation_signature","submit_replication":"https://pith.science/pith/WOFFQIQ43ZWSNQRYNGNG2J3OEX/action/replication_record"}},"created_at":"2026-05-18T00:18:06.423634+00:00","updated_at":"2026-05-18T00:18:06.423634+00:00"}