{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ACCYOB25MJPRY4SMZXX3CERJWN","short_pith_number":"pith:ACCYOB25","schema_version":"1.0","canonical_sha256":"008587075d625f1c724ccdefb11229b37556eb0928e7e584edbb85e84e0fd281","source":{"kind":"arxiv","id":"1906.09444","version":1},"attestation_state":"computed","paper":{"title":"Retrieving Sequential Information for Non-Autoregressive 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":"Chenze Shao, Fandong Meng, Jie Zhou, Jinchao Zhang, Xilin Chen, Yang Feng","submitted_at":"2019-06-22T13:20:57Z","abstract_excerpt":"Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information. Over-translation and under-translation errors often occur for the above reason, especially in the long sentence translation scenario. In this paper, we propose two approaches to retrieve the target sequential information for NAT to enhance its translation ability while preserving the fast-decoding property. Firstly, we propose a sequence-level training method based on a "},"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":"1906.09444","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-22T13:20:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2d4e36313160aff9d6da88e220600947e24149a7bc0c22b4e200ff3ae40b0a1a","abstract_canon_sha256":"f2f69503c69385e7fda55ced36d76c4a9fbe32ec7b60ffe95796f7eede38c410"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:38.021933Z","signature_b64":"GFMRzVEdEPYYXBwMqouWrya52T5hOzPuOR5wlJuPu/33gT2ZluADbELOcVLNohEVOJdmi1d/nH8Z2Lk5bravBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"008587075d625f1c724ccdefb11229b37556eb0928e7e584edbb85e84e0fd281","last_reissued_at":"2026-05-17T23:42:38.021224Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:38.021224Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieving Sequential Information for Non-Autoregressive 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":"Chenze Shao, Fandong Meng, Jie Zhou, Jinchao Zhang, Xilin Chen, Yang Feng","submitted_at":"2019-06-22T13:20:57Z","abstract_excerpt":"Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information. Over-translation and under-translation errors often occur for the above reason, especially in the long sentence translation scenario. In this paper, we propose two approaches to retrieve the target sequential information for NAT to enhance its translation ability while preserving the fast-decoding property. Firstly, we propose a sequence-level training method based on a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09444","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":"1906.09444","created_at":"2026-05-17T23:42:38.021330+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09444v1","created_at":"2026-05-17T23:42:38.021330+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09444","created_at":"2026-05-17T23:42:38.021330+00:00"},{"alias_kind":"pith_short_12","alias_value":"ACCYOB25MJPR","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"ACCYOB25MJPRY4SM","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"ACCYOB25","created_at":"2026-05-18T12:33:12.712433+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/ACCYOB25MJPRY4SMZXX3CERJWN","json":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN.json","graph_json":"https://pith.science/api/pith-number/ACCYOB25MJPRY4SMZXX3CERJWN/graph.json","events_json":"https://pith.science/api/pith-number/ACCYOB25MJPRY4SMZXX3CERJWN/events.json","paper":"https://pith.science/paper/ACCYOB25"},"agent_actions":{"view_html":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN","download_json":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN.json","view_paper":"https://pith.science/paper/ACCYOB25","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09444&json=true","fetch_graph":"https://pith.science/api/pith-number/ACCYOB25MJPRY4SMZXX3CERJWN/graph.json","fetch_events":"https://pith.science/api/pith-number/ACCYOB25MJPRY4SMZXX3CERJWN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN/action/storage_attestation","attest_author":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN/action/author_attestation","sign_citation":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN/action/citation_signature","submit_replication":"https://pith.science/pith/ACCYOB25MJPRY4SMZXX3CERJWN/action/replication_record"}},"created_at":"2026-05-17T23:42:38.021330+00:00","updated_at":"2026-05-17T23:42:38.021330+00:00"}