{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XTCYESLUCMQ5STZXNI5Q6PYNLQ","short_pith_number":"pith:XTCYESLU","schema_version":"1.0","canonical_sha256":"bcc58249741321d94f376a3b0f3f0d5c18c54b4f3ff5361ab85d6a7c68a547be","source":{"kind":"arxiv","id":"1806.03692","version":1},"attestation_state":"computed","paper":{"title":"Deconvolution-Based Global Decoding for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinsong Su, Junyang Lin, Qi Su, Shuming Ma, Xuancheng Ren, Xu Sun","submitted_at":"2018-06-10T17:05:31Z","abstract_excerpt":"A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have proved that language is not linear word sequence but sequence of complex structure, translation at each step should be conditioned on the whole target-side context. To tackle the problem, we propose a new NMT model that decodes the sequence with the guidance of its structural prediction of the context of the target sequence. Our model generates translation based"},"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":"1806.03692","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T17:05:31Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5205e4459bfc2e823fa6621b90d86f85fb91a1fe50d61ee23e5e1c6427ba135c","abstract_canon_sha256":"9def11f809642c308c1865d05f354f739085ac07651c98a6a6b129df2a41765b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:21.193725Z","signature_b64":"GKqjkdYQN9NRbsQJi7Vun0L1whSeGNng4kR3M5CYDmqY/nW9HzDmj3MAeB10nxr+H9vrMMvRlTC23Na3XbDlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcc58249741321d94f376a3b0f3f0d5c18c54b4f3ff5361ab85d6a7c68a547be","last_reissued_at":"2026-05-18T00:13:21.193174Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:21.193174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deconvolution-Based Global Decoding for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinsong Su, Junyang Lin, Qi Su, Shuming Ma, Xuancheng Ren, Xu Sun","submitted_at":"2018-06-10T17:05:31Z","abstract_excerpt":"A great proportion of sequence-to-sequence (Seq2Seq) models for Neural Machine Translation (NMT) adopt Recurrent Neural Network (RNN) to generate translation word by word following a sequential order. As the studies of linguistics have proved that language is not linear word sequence but sequence of complex structure, translation at each step should be conditioned on the whole target-side context. To tackle the problem, we propose a new NMT model that decodes the sequence with the guidance of its structural prediction of the context of the target sequence. Our model generates translation based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03692","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":"1806.03692","created_at":"2026-05-18T00:13:21.193249+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03692v1","created_at":"2026-05-18T00:13:21.193249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03692","created_at":"2026-05-18T00:13:21.193249+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTCYESLUCMQ5","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTCYESLUCMQ5STZX","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTCYESLU","created_at":"2026-05-18T12:33:01.666342+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/XTCYESLUCMQ5STZXNI5Q6PYNLQ","json":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ.json","graph_json":"https://pith.science/api/pith-number/XTCYESLUCMQ5STZXNI5Q6PYNLQ/graph.json","events_json":"https://pith.science/api/pith-number/XTCYESLUCMQ5STZXNI5Q6PYNLQ/events.json","paper":"https://pith.science/paper/XTCYESLU"},"agent_actions":{"view_html":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ","download_json":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ.json","view_paper":"https://pith.science/paper/XTCYESLU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03692&json=true","fetch_graph":"https://pith.science/api/pith-number/XTCYESLUCMQ5STZXNI5Q6PYNLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XTCYESLUCMQ5STZXNI5Q6PYNLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ/action/storage_attestation","attest_author":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ/action/author_attestation","sign_citation":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ/action/citation_signature","submit_replication":"https://pith.science/pith/XTCYESLUCMQ5STZXNI5Q6PYNLQ/action/replication_record"}},"created_at":"2026-05-18T00:13:21.193249+00:00","updated_at":"2026-05-18T00:13:21.193249+00:00"}