{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JKJ3KTNWBF3BSR2CVZ5O4XI2O2","short_pith_number":"pith:JKJ3KTNW","schema_version":"1.0","canonical_sha256":"4a93b54db60976194742ae7aee5d1a7683f1114daffc39983403f0e259a1abbd","source":{"kind":"arxiv","id":"1711.11221","version":3},"attestation_state":"computed","paper":{"title":"Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Guodong Zhou, Shaohui Kuang, Weihua Luo","submitted_at":"2017-11-30T04:30:53Z","abstract_excerpt":"Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text. Current neural machine translation (NMT) systems translate a text in a conventional sentence-by-sentence fashion, ignoring such cross-sentence links and dependencies. This may lead to generate an incoherent target text for a coherent source text. In order to handle this issue, we propose a cache-based approach to modeling coherence for neural machine translation by capturing contextual information either from recently translated sentences or the entire document. Particularl"},"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":"1711.11221","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-30T04:30:53Z","cross_cats_sorted":[],"title_canon_sha256":"e2c432e6c78966db73a0a0081f3b65e91abc73bf69e2ee4de1390c7b2c6f0da1","abstract_canon_sha256":"f954fffbf9a030898ffca3cdb75185a82f3bb03f5074e22428ef3a836a9a0e0a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:19.486004Z","signature_b64":"QU6E4hfHSVka0jAm2ZneqUlJ/3FbODvV/EjdmMKlE9AKV+VLVPCcWDdJuoIya+DdRVVJdyO51sOgGteVpphpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a93b54db60976194742ae7aee5d1a7683f1114daffc39983403f0e259a1abbd","last_reissued_at":"2026-05-18T00:13:19.485346Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:19.485346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Deyi Xiong, Guodong Zhou, Shaohui Kuang, Weihua Luo","submitted_at":"2017-11-30T04:30:53Z","abstract_excerpt":"Sentences in a well-formed text are connected to each other via various links to form the cohesive structure of the text. Current neural machine translation (NMT) systems translate a text in a conventional sentence-by-sentence fashion, ignoring such cross-sentence links and dependencies. This may lead to generate an incoherent target text for a coherent source text. In order to handle this issue, we propose a cache-based approach to modeling coherence for neural machine translation by capturing contextual information either from recently translated sentences or the entire document. Particularl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.11221","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":"1711.11221","created_at":"2026-05-18T00:13:19.485448+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.11221v3","created_at":"2026-05-18T00:13:19.485448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.11221","created_at":"2026-05-18T00:13:19.485448+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKJ3KTNWBF3B","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKJ3KTNWBF3BSR2C","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKJ3KTNW","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20334","citing_title":"An Explainable Approach to Document-level Translation Evaluation with Topic Modeling","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2","json":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2.json","graph_json":"https://pith.science/api/pith-number/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/graph.json","events_json":"https://pith.science/api/pith-number/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/events.json","paper":"https://pith.science/paper/JKJ3KTNW"},"agent_actions":{"view_html":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2","download_json":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2.json","view_paper":"https://pith.science/paper/JKJ3KTNW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.11221&json=true","fetch_graph":"https://pith.science/api/pith-number/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/graph.json","fetch_events":"https://pith.science/api/pith-number/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/action/storage_attestation","attest_author":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/action/author_attestation","sign_citation":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/action/citation_signature","submit_replication":"https://pith.science/pith/JKJ3KTNWBF3BSR2CVZ5O4XI2O2/action/replication_record"}},"created_at":"2026-05-18T00:13:19.485448+00:00","updated_at":"2026-05-18T00:13:19.485448+00:00"}