{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:5WMQTGU76BOLMEX2IRU6YNGAUU","short_pith_number":"pith:5WMQTGU7","schema_version":"1.0","canonical_sha256":"ed99099a9ff05cb612fa4469ec34c0a534339b1c8e14abb94bac99061c32f8cb","source":{"kind":"arxiv","id":"2102.08220","version":1},"attestation_state":"computed","paper":{"title":"Non-Autoregressive Text Generation with Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Vandyke, Deng Cai, Nigel Collier, Piji Li, Simon Baker, Yan Wang, Yixuan Su","submitted_at":"2021-02-16T15:30:33Z","abstract_excerpt":"Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance. Additionally, we devise mechanisms to alleviate the two common problems of vanilla NAG models: the inflexibility of prefixed output length and the conditional independence of individual token predictions. Lastly, to further increase the speed advantage of the proposed mode"},"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":"2102.08220","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-16T15:30:33Z","cross_cats_sorted":[],"title_canon_sha256":"228c1f2b3ab38b7e5049418bb5259d664d605c89e764953ef3b882423746d284","abstract_canon_sha256":"07fa2be21c7e0e8dcbd34f593f19db7a6208bdbfb41828d3ae946ea67fee3512"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:47.512428Z","signature_b64":"8tAZa8lXGpR5wm8tmWEmkPy/CERoDGBa7G4h9e89pXvboF/vjDtCAcVJ4isSfBNSqKs2w/KaqirAVtNrMl+4BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed99099a9ff05cb612fa4469ec34c0a534339b1c8e14abb94bac99061c32f8cb","last_reissued_at":"2026-07-05T02:15:47.512058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:47.512058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Autoregressive Text Generation with Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Vandyke, Deng Cai, Nigel Collier, Piji Li, Simon Baker, Yan Wang, Yixuan Su","submitted_at":"2021-02-16T15:30:33Z","abstract_excerpt":"Non-autoregressive generation (NAG) has recently attracted great attention due to its fast inference speed. However, the generation quality of existing NAG models still lags behind their autoregressive counterparts. In this work, we show that BERT can be employed as the backbone of a NAG model to greatly improve performance. Additionally, we devise mechanisms to alleviate the two common problems of vanilla NAG models: the inflexibility of prefixed output length and the conditional independence of individual token predictions. Lastly, to further increase the speed advantage of the proposed mode"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08220","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2102.08220/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2102.08220","created_at":"2026-07-05T02:15:47.512110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08220v1","created_at":"2026-07-05T02:15:47.512110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08220","created_at":"2026-07-05T02:15:47.512110+00:00"},{"alias_kind":"pith_short_12","alias_value":"5WMQTGU76BOL","created_at":"2026-07-05T02:15:47.512110+00:00"},{"alias_kind":"pith_short_16","alias_value":"5WMQTGU76BOLMEX2","created_at":"2026-07-05T02:15:47.512110+00:00"},{"alias_kind":"pith_short_8","alias_value":"5WMQTGU7","created_at":"2026-07-05T02:15:47.512110+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/5WMQTGU76BOLMEX2IRU6YNGAUU","json":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU.json","graph_json":"https://pith.science/api/pith-number/5WMQTGU76BOLMEX2IRU6YNGAUU/graph.json","events_json":"https://pith.science/api/pith-number/5WMQTGU76BOLMEX2IRU6YNGAUU/events.json","paper":"https://pith.science/paper/5WMQTGU7"},"agent_actions":{"view_html":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU","download_json":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU.json","view_paper":"https://pith.science/paper/5WMQTGU7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08220&json=true","fetch_graph":"https://pith.science/api/pith-number/5WMQTGU76BOLMEX2IRU6YNGAUU/graph.json","fetch_events":"https://pith.science/api/pith-number/5WMQTGU76BOLMEX2IRU6YNGAUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU/action/storage_attestation","attest_author":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU/action/author_attestation","sign_citation":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU/action/citation_signature","submit_replication":"https://pith.science/pith/5WMQTGU76BOLMEX2IRU6YNGAUU/action/replication_record"}},"created_at":"2026-07-05T02:15:47.512110+00:00","updated_at":"2026-07-05T02:15:47.512110+00:00"}