{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FYWGW25KLN5GAH26P4PF4JOLVP","short_pith_number":"pith:FYWGW25K","schema_version":"1.0","canonical_sha256":"2e2c6b6baa5b7a601f5e7f1e5e25cbabe285b653eb940e30e4d30c036af998a1","source":{"kind":"arxiv","id":"1812.09664","version":1},"attestation_state":"computed","paper":{"title":"Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Di He, Junliang Guo, Linli Xu, Tao Qin, Tie-Yan Liu, Xu Tan","submitted_at":"2018-12-23T06:28:30Z","abstract_excerpt":"Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive translation (AT) models. Previous work shows that the quality of the inputs of the decoder is important and largely impacts the model accuracy. In this paper, we propose two methods to enhance the decoder inputs so as to improve NAT models. The first one directly leverages a phrase table generated by conventional SMT approaches to translate source tokens to targe"},"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":"1812.09664","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-12-23T06:28:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c73e04c34ed270395c84e5ebc4e3bf24f2228188140e4101d7193c76847b1928","abstract_canon_sha256":"1def436b4085f930f729ca394fc02e175b6a47f588e291dc51e88c2332556574"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:27.200763Z","signature_b64":"hlDKfkJWtZmr762rDLufhVcERK0MlJISYTXN4vbReIhFFHdfuXZGW/2E7Wor3v0dkIR6VCWb1MvImZdQ7G2fBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e2c6b6baa5b7a601f5e7f1e5e25cbabe285b653eb940e30e4d30c036af998a1","last_reissued_at":"2026-05-17T23:57:27.200083Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:27.200083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Autoregressive Neural Machine Translation with Enhanced Decoder Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Di He, Junliang Guo, Linli Xu, Tao Qin, Tie-Yan Liu, Xu Tan","submitted_at":"2018-12-23T06:28:30Z","abstract_excerpt":"Non-autoregressive translation (NAT) models, which remove the dependence on previous target tokens from the inputs of the decoder, achieve significantly inference speedup but at the cost of inferior accuracy compared to autoregressive translation (AT) models. Previous work shows that the quality of the inputs of the decoder is important and largely impacts the model accuracy. In this paper, we propose two methods to enhance the decoder inputs so as to improve NAT models. The first one directly leverages a phrase table generated by conventional SMT approaches to translate source tokens to targe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.09664","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":"1812.09664","created_at":"2026-05-17T23:57:27.200191+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.09664v1","created_at":"2026-05-17T23:57:27.200191+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.09664","created_at":"2026-05-17T23:57:27.200191+00:00"},{"alias_kind":"pith_short_12","alias_value":"FYWGW25KLN5G","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"FYWGW25KLN5GAH26","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"FYWGW25K","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.09444","citing_title":"Retrieving Sequential Information for Non-Autoregressive Neural Machine Translation","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP","json":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP.json","graph_json":"https://pith.science/api/pith-number/FYWGW25KLN5GAH26P4PF4JOLVP/graph.json","events_json":"https://pith.science/api/pith-number/FYWGW25KLN5GAH26P4PF4JOLVP/events.json","paper":"https://pith.science/paper/FYWGW25K"},"agent_actions":{"view_html":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP","download_json":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP.json","view_paper":"https://pith.science/paper/FYWGW25K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.09664&json=true","fetch_graph":"https://pith.science/api/pith-number/FYWGW25KLN5GAH26P4PF4JOLVP/graph.json","fetch_events":"https://pith.science/api/pith-number/FYWGW25KLN5GAH26P4PF4JOLVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP/action/storage_attestation","attest_author":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP/action/author_attestation","sign_citation":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP/action/citation_signature","submit_replication":"https://pith.science/pith/FYWGW25KLN5GAH26P4PF4JOLVP/action/replication_record"}},"created_at":"2026-05-17T23:57:27.200191+00:00","updated_at":"2026-05-17T23:57:27.200191+00:00"}