{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DFOZ77QYUVKO7H37BMPNJ3GLLB","short_pith_number":"pith:DFOZ77QY","schema_version":"1.0","canonical_sha256":"195d9ffe18a554ef9f7f0b1ed4eccb584f423e00ec33cc3e441af34d89f58412","source":{"kind":"arxiv","id":"1711.09502","version":2},"attestation_state":"computed","paper":{"title":"Modeling Past and Future for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Jiajun Chen, Lili Mou, Shujian Huang, Xinyu Dai, Zaixiang Zheng, Zhaopeng Tu","submitted_at":"2017-11-27T01:42:00Z","abstract_excerpt":"Existing neural machine translation systems do not explicitly model what has been translated and what has not during the decoding phase. To address this problem, we propose a novel mechanism that separates the source information into two parts: translated Past contents and untranslated Future contents, which are modeled by two additional recurrent layers. The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents. Experimental results show that the proposed approach significantly improv"},"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":"1711.09502","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-27T01:42:00Z","cross_cats_sorted":[],"title_canon_sha256":"e265e9f974419d4d90a636992e968a597af03252a235ab4da981436858860d19","abstract_canon_sha256":"30a7629e3c9613110d5b6ba7adfc45580c9dadb6616404986654a2cb1431c38a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:17.620058Z","signature_b64":"1sOmq8zpMpEijc6+i64z2KPI4Qxv4bO0ZnC8sRCLKvoRV7n2QVvNne4hOlpAXRtI/fioqYJhY6fq3DyouqecBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"195d9ffe18a554ef9f7f0b1ed4eccb584f423e00ec33cc3e441af34d89f58412","last_reissued_at":"2026-05-18T00:27:17.619611Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:17.619611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Past and Future for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Zhou, Jiajun Chen, Lili Mou, Shujian Huang, Xinyu Dai, Zaixiang Zheng, Zhaopeng Tu","submitted_at":"2017-11-27T01:42:00Z","abstract_excerpt":"Existing neural machine translation systems do not explicitly model what has been translated and what has not during the decoding phase. To address this problem, we propose a novel mechanism that separates the source information into two parts: translated Past contents and untranslated Future contents, which are modeled by two additional recurrent layers. The Past and Future contents are fed to both the attention model and the decoder states, which offers NMT systems the knowledge of translated and untranslated contents. Experimental results show that the proposed approach significantly improv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.09502","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":"1711.09502","created_at":"2026-05-18T00:27:17.619681+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.09502v2","created_at":"2026-05-18T00:27:17.619681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.09502","created_at":"2026-05-18T00:27:17.619681+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFOZ77QYUVKO","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFOZ77QYUVKO7H37","created_at":"2026-05-18T12:31:10.602751+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFOZ77QY","created_at":"2026-05-18T12:31:10.602751+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/DFOZ77QYUVKO7H37BMPNJ3GLLB","json":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB.json","graph_json":"https://pith.science/api/pith-number/DFOZ77QYUVKO7H37BMPNJ3GLLB/graph.json","events_json":"https://pith.science/api/pith-number/DFOZ77QYUVKO7H37BMPNJ3GLLB/events.json","paper":"https://pith.science/paper/DFOZ77QY"},"agent_actions":{"view_html":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB","download_json":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB.json","view_paper":"https://pith.science/paper/DFOZ77QY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.09502&json=true","fetch_graph":"https://pith.science/api/pith-number/DFOZ77QYUVKO7H37BMPNJ3GLLB/graph.json","fetch_events":"https://pith.science/api/pith-number/DFOZ77QYUVKO7H37BMPNJ3GLLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB/action/storage_attestation","attest_author":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB/action/author_attestation","sign_citation":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB/action/citation_signature","submit_replication":"https://pith.science/pith/DFOZ77QYUVKO7H37BMPNJ3GLLB/action/replication_record"}},"created_at":"2026-05-18T00:27:17.619681+00:00","updated_at":"2026-05-18T00:27:17.619681+00:00"}