{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3JGML3ES55WYYIH5I4FPTUEN5Z","short_pith_number":"pith:3JGML3ES","schema_version":"1.0","canonical_sha256":"da4cc5ec92ef6d8c20fd470af9d08dee5e913fe2e309fecedebb3f449255637c","source":{"kind":"arxiv","id":"1906.01543","version":2},"attestation_state":"computed","paper":{"title":"Training Neural Response Selection for Task-Oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Gerz, Georgios Spithourakis, I\\~nigo Casanueva, Ivan Vuli\\'c, Matthew Henderson, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Sam Coope, Tsung-Hsien Wen","submitted_at":"2019-06-04T15:58:54Z","abstract_excerpt":"Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks. Inspired by the recent success of pretraining in language modelling, we propose an effective method for deploying response selection in task-oriented dialogue. To train response selection models for task-oriented dialogue tasks, we propose a novel method which: 1) pretrains the response selection model on large general-domain conversational corpora; and the"},"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":"1906.01543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-06-04T15:58:54Z","cross_cats_sorted":[],"title_canon_sha256":"22a7f0197afd2f39592743dfaef03804d6c3060fed1796dc931cd4a209d5b17e","abstract_canon_sha256":"db87b234e3fb7c04b829a706cb3ed7f8ec0dd48d616dfbadd3e86fb16e3b326f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:55.883436Z","signature_b64":"ifX2aoaoBpTJY+tj0aUekTyv2C9HLLAlucTIx+au67F0yJH75uBBY0aO/G/wLpPKN28YdA4VXDK4mNfWYLe7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da4cc5ec92ef6d8c20fd470af9d08dee5e913fe2e309fecedebb3f449255637c","last_reissued_at":"2026-05-17T23:43:55.882798Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:55.882798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Neural Response Selection for Task-Oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniela Gerz, Georgios Spithourakis, I\\~nigo Casanueva, Ivan Vuli\\'c, Matthew Henderson, Nikola Mrk\\v{s}i\\'c, Pawe{\\l} Budzianowski, Pei-Hao Su, Sam Coope, Tsung-Hsien Wen","submitted_at":"2019-06-04T15:58:54Z","abstract_excerpt":"Despite their popularity in the chatbot literature, retrieval-based models have had modest impact on task-oriented dialogue systems, with the main obstacle to their application being the low-data regime of most task-oriented dialogue tasks. Inspired by the recent success of pretraining in language modelling, we propose an effective method for deploying response selection in task-oriented dialogue. To train response selection models for task-oriented dialogue tasks, we propose a novel method which: 1) pretrains the response selection model on large general-domain conversational corpora; and the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.01543","kind":"arxiv","version":2},"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":"1906.01543","created_at":"2026-05-17T23:43:55.882886+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.01543v2","created_at":"2026-05-17T23:43:55.882886+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.01543","created_at":"2026-05-17T23:43:55.882886+00:00"},{"alias_kind":"pith_short_12","alias_value":"3JGML3ES55WY","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"3JGML3ES55WYYIH5","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"3JGML3ES","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/3JGML3ES55WYYIH5I4FPTUEN5Z","json":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z.json","graph_json":"https://pith.science/api/pith-number/3JGML3ES55WYYIH5I4FPTUEN5Z/graph.json","events_json":"https://pith.science/api/pith-number/3JGML3ES55WYYIH5I4FPTUEN5Z/events.json","paper":"https://pith.science/paper/3JGML3ES"},"agent_actions":{"view_html":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z","download_json":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z.json","view_paper":"https://pith.science/paper/3JGML3ES","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.01543&json=true","fetch_graph":"https://pith.science/api/pith-number/3JGML3ES55WYYIH5I4FPTUEN5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/3JGML3ES55WYYIH5I4FPTUEN5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z/action/storage_attestation","attest_author":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z/action/author_attestation","sign_citation":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z/action/citation_signature","submit_replication":"https://pith.science/pith/3JGML3ES55WYYIH5I4FPTUEN5Z/action/replication_record"}},"created_at":"2026-05-17T23:43:55.882886+00:00","updated_at":"2026-05-17T23:43:55.882886+00:00"}