{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LABBWTXZEYG3RTEEGUKJBCZ4FB","short_pith_number":"pith:LABBWTXZ","schema_version":"1.0","canonical_sha256":"58021b4ef9260db8cc843514908b3c28671f513c7932c3e9c9ab9650b8eb20b3","source":{"kind":"arxiv","id":"1809.04276","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Enhanced Adversarial Training for Neural Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Qingfu Zhu, Ting Liu, Weinan Zhang","submitted_at":"2018-09-12T06:47:21Z","abstract_excerpt":"Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows "},"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":"1809.04276","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-12T06:47:21Z","cross_cats_sorted":[],"title_canon_sha256":"04015131f2dbd47f5bc7f487ca27e31fbddc1e07e3b10bda96039b6f20fb192e","abstract_canon_sha256":"6c6232d3f0b05cc75a84582314cb1e66f55b38b0a6356169310d92f5b2b76514"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:20.700225Z","signature_b64":"RpDvNClQUayHe736svoWVqo47L57sN2wZvT56fOvQcn3sFPsu57Ocn2+VTUHflugJJfcz8m0lA5Cg12UBuYJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58021b4ef9260db8cc843514908b3c28671f513c7932c3e9c9ab9650b8eb20b3","last_reissued_at":"2026-05-17T23:45:20.699702Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:20.699702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Enhanced Adversarial Training for Neural Response Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Lei Cui, Qingfu Zhu, Ting Liu, Weinan Zhang","submitted_at":"2018-09-12T06:47:21Z","abstract_excerpt":"Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method for neural response generation. Distinct from existing approaches, the REAT method leverages an encoder-decoder framework in terms of an adversarial training paradigm, while taking advantage of N-best response candidates from a retrieval-based system to construct the discriminator. An empirical study on a large scale public available benchmark dataset shows "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04276","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":"1809.04276","created_at":"2026-05-17T23:45:20.699759+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.04276v2","created_at":"2026-05-17T23:45:20.699759+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04276","created_at":"2026-05-17T23:45:20.699759+00:00"},{"alias_kind":"pith_short_12","alias_value":"LABBWTXZEYG3","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_16","alias_value":"LABBWTXZEYG3RTEE","created_at":"2026-05-18T12:32:33.847187+00:00"},{"alias_kind":"pith_short_8","alias_value":"LABBWTXZ","created_at":"2026-05-18T12:32:33.847187+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/LABBWTXZEYG3RTEEGUKJBCZ4FB","json":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB.json","graph_json":"https://pith.science/api/pith-number/LABBWTXZEYG3RTEEGUKJBCZ4FB/graph.json","events_json":"https://pith.science/api/pith-number/LABBWTXZEYG3RTEEGUKJBCZ4FB/events.json","paper":"https://pith.science/paper/LABBWTXZ"},"agent_actions":{"view_html":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB","download_json":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB.json","view_paper":"https://pith.science/paper/LABBWTXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.04276&json=true","fetch_graph":"https://pith.science/api/pith-number/LABBWTXZEYG3RTEEGUKJBCZ4FB/graph.json","fetch_events":"https://pith.science/api/pith-number/LABBWTXZEYG3RTEEGUKJBCZ4FB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB/action/storage_attestation","attest_author":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB/action/author_attestation","sign_citation":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB/action/citation_signature","submit_replication":"https://pith.science/pith/LABBWTXZEYG3RTEEGUKJBCZ4FB/action/replication_record"}},"created_at":"2026-05-17T23:45:20.699759+00:00","updated_at":"2026-05-17T23:45:20.699759+00:00"}