{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IEKJE2AYGA55VHYCXYVHCNRUIQ","short_pith_number":"pith:IEKJE2AY","schema_version":"1.0","canonical_sha256":"4114926818303bda9f02be2a7136344406bd09e1c00086809739e85fd5aebe93","source":{"kind":"arxiv","id":"2010.06138","version":1},"attestation_state":"computed","paper":{"title":"Incorporating BERT into Parallel Sequence Decoding with Adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boxing Chen, Enhong Chen, Hao-Ran Wei, Junliang Guo, Linli Xu, Zhirui Zhang","submitted_at":"2020-10-13T03:25:15Z","abstract_excerpt":"While large scale pre-trained language models such as BERT have achieved great success on various natural language understanding tasks, how to efficiently and effectively incorporate them into sequence-to-sequence models and the corresponding text generation tasks remains a non-trivial problem. In this paper, we propose to address this problem by taking two different BERT models as the encoder and decoder respectively, and fine-tuning them by introducing simple and lightweight adapter modules, which are inserted between BERT layers and tuned on the task-specific dataset. In this way, we obtain"},"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":"2010.06138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-13T03:25:15Z","cross_cats_sorted":[],"title_canon_sha256":"5f0381f3aa77f4f315d86c1c4ebe33fb84c26a8c0f97f5ff27f60915c35f03e1","abstract_canon_sha256":"27e7568c12fb570f81c06ea7d9c8ddae58dabe55e4498ff4ce380e96a657fab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:42:24.321417Z","signature_b64":"CaLLs3IjSq01OZ0OuVcJ9smChXGDpNpwRJpA6HsriXsGnL1WmWkm5NxsqpxyT3RjSWAuUJBMhuMqQwGUFTb2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4114926818303bda9f02be2a7136344406bd09e1c00086809739e85fd5aebe93","last_reissued_at":"2026-07-05T01:42:24.321065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:42:24.321065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating BERT into Parallel Sequence Decoding with Adapters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boxing Chen, Enhong Chen, Hao-Ran Wei, Junliang Guo, Linli Xu, Zhirui Zhang","submitted_at":"2020-10-13T03:25:15Z","abstract_excerpt":"While large scale pre-trained language models such as BERT have achieved great success on various natural language understanding tasks, how to efficiently and effectively incorporate them into sequence-to-sequence models and the corresponding text generation tasks remains a non-trivial problem. In this paper, we propose to address this problem by taking two different BERT models as the encoder and decoder respectively, and fine-tuning them by introducing simple and lightweight adapter modules, which are inserted between BERT layers and tuned on the task-specific dataset. In this way, we obtain"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06138","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/2010.06138/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":"2010.06138","created_at":"2026-07-05T01:42:24.321125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06138v1","created_at":"2026-07-05T01:42:24.321125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06138","created_at":"2026-07-05T01:42:24.321125+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEKJE2AYGA55","created_at":"2026-07-05T01:42:24.321125+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEKJE2AYGA55VHYC","created_at":"2026-07-05T01:42:24.321125+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEKJE2AY","created_at":"2026-07-05T01:42:24.321125+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/IEKJE2AYGA55VHYCXYVHCNRUIQ","json":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ.json","graph_json":"https://pith.science/api/pith-number/IEKJE2AYGA55VHYCXYVHCNRUIQ/graph.json","events_json":"https://pith.science/api/pith-number/IEKJE2AYGA55VHYCXYVHCNRUIQ/events.json","paper":"https://pith.science/paper/IEKJE2AY"},"agent_actions":{"view_html":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ","download_json":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ.json","view_paper":"https://pith.science/paper/IEKJE2AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06138&json=true","fetch_graph":"https://pith.science/api/pith-number/IEKJE2AYGA55VHYCXYVHCNRUIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/IEKJE2AYGA55VHYCXYVHCNRUIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ/action/storage_attestation","attest_author":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ/action/author_attestation","sign_citation":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ/action/citation_signature","submit_replication":"https://pith.science/pith/IEKJE2AYGA55VHYCXYVHCNRUIQ/action/replication_record"}},"created_at":"2026-07-05T01:42:24.321125+00:00","updated_at":"2026-07-05T01:42:24.321125+00:00"}