{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2DKRYVYUY4WPHZVTCYX5U6AW5W","short_pith_number":"pith:2DKRYVYU","schema_version":"1.0","canonical_sha256":"d0d51c5714c72cf3e6b3162fda7816edbd5a26915af610bf6d696d10b77ae716","source":{"kind":"arxiv","id":"1907.05346","version":1},"attestation_state":"computed","paper":{"title":"A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiahuan Pei, Maarten de Rijke, Pengjie Ren","submitted_at":"2019-07-10T13:25:50Z","abstract_excerpt":"End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a single-module model to generate responses for complex dialogue contexts. However, no model consistently outperforms the others in all cases. We propose a neural Modular Task-oriented Dialogue System(MTDS) framework, in which a few expert bots are combined to generate the response for a given dialogue context. MTDS consists of a chair bot and several expert bots. Each expert bot "},"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":"1907.05346","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-10T13:25:50Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"df7d2f431eef81c95329955c9a347e091afe0471fc8921efdb120993f1c40faa","abstract_canon_sha256":"27e41928b132293c99e332dd34d3d1f406c34eb659730d95e6658adf707fbded"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:50.638486Z","signature_b64":"oE80f6glCqj49a62eDUNF6fTsDQl2kZFM5ijC+yzk1R6uK7kbq6hHCqsvg0+QBBkkJJRI0fE3NJ/LfdARQ6dCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d51c5714c72cf3e6b3162fda7816edbd5a26915af610bf6d696d10b77ae716","last_reissued_at":"2026-05-17T23:40:50.637901Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:50.637901Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Modular Task-oriented Dialogue System Using a Neural Mixture-of-Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiahuan Pei, Maarten de Rijke, Pengjie Ren","submitted_at":"2019-07-10T13:25:50Z","abstract_excerpt":"End-to-end Task-oriented Dialogue Systems (TDSs) have attracted a lot of attention for their superiority (e.g., in terms of global optimization) over pipeline modularized TDSs. Previous studies on end-to-end TDSs use a single-module model to generate responses for complex dialogue contexts. However, no model consistently outperforms the others in all cases. We propose a neural Modular Task-oriented Dialogue System(MTDS) framework, in which a few expert bots are combined to generate the response for a given dialogue context. MTDS consists of a chair bot and several expert bots. Each expert bot "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.05346","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":"1907.05346","created_at":"2026-05-17T23:40:50.637979+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.05346v1","created_at":"2026-05-17T23:40:50.637979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.05346","created_at":"2026-05-17T23:40:50.637979+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DKRYVYUY4WP","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DKRYVYUY4WPHZVT","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DKRYVYU","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/2DKRYVYUY4WPHZVTCYX5U6AW5W","json":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W.json","graph_json":"https://pith.science/api/pith-number/2DKRYVYUY4WPHZVTCYX5U6AW5W/graph.json","events_json":"https://pith.science/api/pith-number/2DKRYVYUY4WPHZVTCYX5U6AW5W/events.json","paper":"https://pith.science/paper/2DKRYVYU"},"agent_actions":{"view_html":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W","download_json":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W.json","view_paper":"https://pith.science/paper/2DKRYVYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.05346&json=true","fetch_graph":"https://pith.science/api/pith-number/2DKRYVYUY4WPHZVTCYX5U6AW5W/graph.json","fetch_events":"https://pith.science/api/pith-number/2DKRYVYUY4WPHZVTCYX5U6AW5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W/action/storage_attestation","attest_author":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W/action/author_attestation","sign_citation":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W/action/citation_signature","submit_replication":"https://pith.science/pith/2DKRYVYUY4WPHZVTCYX5U6AW5W/action/replication_record"}},"created_at":"2026-05-17T23:40:50.637979+00:00","updated_at":"2026-05-17T23:40:50.637979+00:00"}