{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4PH33FLRJLC3M52XUQV7K77G6B","short_pith_number":"pith:4PH33FLR","schema_version":"1.0","canonical_sha256":"e3cfbd95714ac5b67757a42bf57fe6f04039e3acd9f6fddd150b2f936bb7437b","source":{"kind":"arxiv","id":"1806.11249","version":1},"attestation_state":"computed","paper":{"title":"Neural Machine Translation with Key-Value Memory-Augmented Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Wang, Fandong Meng, Haiyang Wu, Junjie Zhai, Yong Cheng, Yuekui Yang, Zhaopeng Tu","submitted_at":"2018-06-29T02:06:00Z","abstract_excerpt":"Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value memory-augmented attention model for NMT, called KVMEMATT. Specifically, we maintain a timely updated keymemory to keep track of attention history and a fixed value-memory to store the representation of source sentence throughout the whole translation process. Via nontrivial transformations and iterative interactions between the two memories, the decoder focuses on"},"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":"1806.11249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-29T02:06:00Z","cross_cats_sorted":[],"title_canon_sha256":"6bd32d79b5a9117391598d99178f5be672b8aa421d3b375e1b7fdbce2c95797c","abstract_canon_sha256":"1ce0ef73b2338e229ff88afd56a8cd2537858ada25a5a0f26c3321baa876e1db"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:03.119738Z","signature_b64":"08Z8s8Mahr57DsLbqfn+d31YKnEhhYisqc4bOJKNVbwhVDLC+rcq+FubrrjtaQ9Iyscwnn7ZjCs8h5uj2VViAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3cfbd95714ac5b67757a42bf57fe6f04039e3acd9f6fddd150b2f936bb7437b","last_reissued_at":"2026-05-18T00:12:03.118950Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:03.118950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Machine Translation with Key-Value Memory-Augmented Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Di Wang, Fandong Meng, Haiyang Wu, Junjie Zhai, Yong Cheng, Yuekui Yang, Zhaopeng Tu","submitted_at":"2018-06-29T02:06:00Z","abstract_excerpt":"Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value memory-augmented attention model for NMT, called KVMEMATT. Specifically, we maintain a timely updated keymemory to keep track of attention history and a fixed value-memory to store the representation of source sentence throughout the whole translation process. Via nontrivial transformations and iterative interactions between the two memories, the decoder focuses on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.11249","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":"1806.11249","created_at":"2026-05-18T00:12:03.119071+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.11249v1","created_at":"2026-05-18T00:12:03.119071+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.11249","created_at":"2026-05-18T00:12:03.119071+00:00"},{"alias_kind":"pith_short_12","alias_value":"4PH33FLRJLC3","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4PH33FLRJLC3M52X","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4PH33FLR","created_at":"2026-05-18T12:32:05.422762+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/4PH33FLRJLC3M52XUQV7K77G6B","json":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B.json","graph_json":"https://pith.science/api/pith-number/4PH33FLRJLC3M52XUQV7K77G6B/graph.json","events_json":"https://pith.science/api/pith-number/4PH33FLRJLC3M52XUQV7K77G6B/events.json","paper":"https://pith.science/paper/4PH33FLR"},"agent_actions":{"view_html":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B","download_json":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B.json","view_paper":"https://pith.science/paper/4PH33FLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.11249&json=true","fetch_graph":"https://pith.science/api/pith-number/4PH33FLRJLC3M52XUQV7K77G6B/graph.json","fetch_events":"https://pith.science/api/pith-number/4PH33FLRJLC3M52XUQV7K77G6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B/action/storage_attestation","attest_author":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B/action/author_attestation","sign_citation":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B/action/citation_signature","submit_replication":"https://pith.science/pith/4PH33FLRJLC3M52XUQV7K77G6B/action/replication_record"}},"created_at":"2026-05-18T00:12:03.119071+00:00","updated_at":"2026-05-18T00:12:03.119071+00:00"}