{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:J3Q3YPVAXVNHRDMCPVDZ7AFV34","short_pith_number":"pith:J3Q3YPVA","schema_version":"1.0","canonical_sha256":"4ee1bc3ea0bd5a788d827d479f80b5df09440e530ae3d3187d9d10cb12c11ec6","source":{"kind":"arxiv","id":"1801.05122","version":2},"attestation_state":"computed","paper":{"title":"Asynchronous Bidirectional Decoding for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongji Wang, Jinsong Su, Rongrong Ji, Xiangwen Zhang, Yang Liu, Yue Qin","submitted_at":"2018-01-16T05:21:43Z","abstract_excerpt":"The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright manner, leaving the target-side contexts generated from right to left unexploited during translation. In this paper, we equip the conventional attentional encoder-decoder NMT framework with a backward decoder, in order to explore bidirectional decoding for NMT. Attending to the hidden state sequence produced by the encoder, our backward decoder first learns "},"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":"1801.05122","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-01-16T05:21:43Z","cross_cats_sorted":[],"title_canon_sha256":"5f97ee6ed4f922fd9fb26c9c42f9c5d9fdbafd754a8ae791b19a10f38b682208","abstract_canon_sha256":"406ef3d7aa00e552ed50474f8f4d2787f5b4a09a1d7d616b65d3093465865789"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:24:28.440383Z","signature_b64":"pzFS4s+5m8X4X9ZTeJ2DMJrVZKwZi2v+v/3VlMzKJbkuvTrifA7lY39Vq/u7SFYWxQjEnbRSmM3ksVUVbfw0AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ee1bc3ea0bd5a788d827d479f80b5df09440e530ae3d3187d9d10cb12c11ec6","last_reissued_at":"2026-05-18T00:24:28.439747Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:24:28.439747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Asynchronous Bidirectional Decoding for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongji Wang, Jinsong Su, Rongrong Ji, Xiangwen Zhang, Yang Liu, Yue Qin","submitted_at":"2018-01-16T05:21:43Z","abstract_excerpt":"The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright manner, leaving the target-side contexts generated from right to left unexploited during translation. In this paper, we equip the conventional attentional encoder-decoder NMT framework with a backward decoder, in order to explore bidirectional decoding for NMT. Attending to the hidden state sequence produced by the encoder, our backward decoder first learns "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.05122","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":"1801.05122","created_at":"2026-05-18T00:24:28.439839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1801.05122v2","created_at":"2026-05-18T00:24:28.439839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.05122","created_at":"2026-05-18T00:24:28.439839+00:00"},{"alias_kind":"pith_short_12","alias_value":"J3Q3YPVAXVNH","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"J3Q3YPVAXVNHRDMC","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"J3Q3YPVA","created_at":"2026-05-18T12:32:31.084164+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/J3Q3YPVAXVNHRDMCPVDZ7AFV34","json":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34.json","graph_json":"https://pith.science/api/pith-number/J3Q3YPVAXVNHRDMCPVDZ7AFV34/graph.json","events_json":"https://pith.science/api/pith-number/J3Q3YPVAXVNHRDMCPVDZ7AFV34/events.json","paper":"https://pith.science/paper/J3Q3YPVA"},"agent_actions":{"view_html":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34","download_json":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34.json","view_paper":"https://pith.science/paper/J3Q3YPVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1801.05122&json=true","fetch_graph":"https://pith.science/api/pith-number/J3Q3YPVAXVNHRDMCPVDZ7AFV34/graph.json","fetch_events":"https://pith.science/api/pith-number/J3Q3YPVAXVNHRDMCPVDZ7AFV34/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34/action/storage_attestation","attest_author":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34/action/author_attestation","sign_citation":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34/action/citation_signature","submit_replication":"https://pith.science/pith/J3Q3YPVAXVNHRDMCPVDZ7AFV34/action/replication_record"}},"created_at":"2026-05-18T00:24:28.439839+00:00","updated_at":"2026-05-18T00:24:28.439839+00:00"}