{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:U5RK63LNKMWW6TESNYKJDSL44M","short_pith_number":"pith:U5RK63LN","schema_version":"1.0","canonical_sha256":"a762af6d6d532d6f4c926e1491c97ce32fbe33f79081b0a64cc85d0e391c34cc","source":{"kind":"arxiv","id":"1804.08217","version":3},"attestation_state":"computed","paper":{"title":"Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Pascale Fung","submitted_at":"2018-04-23T01:46:13Z","abstract_excerpt":"End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this issue. Mem2Seq is the first neural generative model that combines the multi-hop attention over memories with the idea of pointer network. We empirically show how Mem2Seq controls each generation step, and how its multi-hop attention mechanism helps in learning correlations between memories. In addition, our model is quite general without complicated task-specif"},"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":"1804.08217","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-23T01:46:13Z","cross_cats_sorted":[],"title_canon_sha256":"ead43c926df0ae53f6027e09d9ba4cfdd80110bcd7e04609136a6a880a6e87c6","abstract_canon_sha256":"83e791eb3f702ccfa3702e55c2ad54673503454cb05076bb9f66edcfe871e7be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:36.269131Z","signature_b64":"QSmRFEYy2EGozHWb1c5aiKGzzMtrbqZIl6PlvN2koi4j6j/YGmgSqLmuaAi4lYE+4A/bi2/ON1HSA3oMkBDjAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a762af6d6d532d6f4c926e1491c97ce32fbe33f79081b0a64cc85d0e391c34cc","last_reissued_at":"2026-05-18T00:15:36.268427Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:36.268427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrea Madotto, Chien-Sheng Wu, Pascale Fung","submitted_at":"2018-04-23T01:46:13Z","abstract_excerpt":"End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable model called memory-to-sequence (Mem2Seq) to address this issue. Mem2Seq is the first neural generative model that combines the multi-hop attention over memories with the idea of pointer network. We empirically show how Mem2Seq controls each generation step, and how its multi-hop attention mechanism helps in learning correlations between memories. In addition, our model is quite general without complicated task-specif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08217","kind":"arxiv","version":3},"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":"1804.08217","created_at":"2026-05-18T00:15:36.268538+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.08217v3","created_at":"2026-05-18T00:15:36.268538+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08217","created_at":"2026-05-18T00:15:36.268538+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5RK63LNKMWW","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5RK63LNKMWW6TES","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5RK63LN","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.14252","citing_title":"From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M","json":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M.json","graph_json":"https://pith.science/api/pith-number/U5RK63LNKMWW6TESNYKJDSL44M/graph.json","events_json":"https://pith.science/api/pith-number/U5RK63LNKMWW6TESNYKJDSL44M/events.json","paper":"https://pith.science/paper/U5RK63LN"},"agent_actions":{"view_html":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M","download_json":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M.json","view_paper":"https://pith.science/paper/U5RK63LN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.08217&json=true","fetch_graph":"https://pith.science/api/pith-number/U5RK63LNKMWW6TESNYKJDSL44M/graph.json","fetch_events":"https://pith.science/api/pith-number/U5RK63LNKMWW6TESNYKJDSL44M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M/action/storage_attestation","attest_author":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M/action/author_attestation","sign_citation":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M/action/citation_signature","submit_replication":"https://pith.science/pith/U5RK63LNKMWW6TESNYKJDSL44M/action/replication_record"}},"created_at":"2026-05-18T00:15:36.268538+00:00","updated_at":"2026-05-18T00:15:36.268538+00:00"}