{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:774XCGOOEOOUBHY6FDK457BI2T","short_pith_number":"pith:774XCGOO","schema_version":"1.0","canonical_sha256":"fff97119ce239d409f1e28d5cefc28d4e139eb532c8cc42dc555e2216950f422","source":{"kind":"arxiv","id":"1908.05672","version":5},"attestation_state":"computed","paper":{"title":"Towards Making the Most of BERT in Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhao, Hao Zhou, Jiacheng Yang, Lei Li, Mingxuan Wang, Weinan Zhang, Yong Yu","submitted_at":"2019-08-15T03:33:50Z","abstract_excerpt":"GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In this work, we introduce a concerted training framework (CTNMT) that is the key to integrate the pre-trained LMs to neural machine translation (NMT). Our proposed CTNMT consists of three techniques: a) asymptotic distillation to ensure that the NMT model can retain the previous pre-trained knowledge; b) a dynamic switching gate to avoid catastrophic forgetti"},"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":"1908.05672","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T03:33:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"14b3dc32f816ebccbf7f796d040affbbe568bf642a86d7b707e112238ea6761f","abstract_canon_sha256":"f3e7b313c4d2ef3ee12dcb5a0d0aa307649419e598262dc37d54724bcd8dea9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:46.323435Z","signature_b64":"OaiwDyDkdLIdiJqMG+kfMpZDJH9pPmCdEm46ok8swRtJO5T7x5TyEwCNWsAmcU/c8OE9BMW/sAxUWDIyZhFZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fff97119ce239d409f1e28d5cefc28d4e139eb532c8cc42dc555e2216950f422","last_reissued_at":"2026-07-05T04:32:46.322934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:46.322934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Making the Most of BERT in Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhao, Hao Zhou, Jiacheng Yang, Lei Li, Mingxuan Wang, Weinan Zhang, Yong Yu","submitted_at":"2019-08-15T03:33:50Z","abstract_excerpt":"GPT-2 and BERT demonstrate the effectiveness of using pre-trained language models (LMs) on various natural language processing tasks. However, LM fine-tuning often suffers from catastrophic forgetting when applied to resource-rich tasks. In this work, we introduce a concerted training framework (CTNMT) that is the key to integrate the pre-trained LMs to neural machine translation (NMT). Our proposed CTNMT consists of three techniques: a) asymptotic distillation to ensure that the NMT model can retain the previous pre-trained knowledge; b) a dynamic switching gate to avoid catastrophic forgetti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05672","kind":"arxiv","version":5},"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/1908.05672/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":"1908.05672","created_at":"2026-07-05T04:32:46.322990+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05672v5","created_at":"2026-07-05T04:32:46.322990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05672","created_at":"2026-07-05T04:32:46.322990+00:00"},{"alias_kind":"pith_short_12","alias_value":"774XCGOOEOOU","created_at":"2026-07-05T04:32:46.322990+00:00"},{"alias_kind":"pith_short_16","alias_value":"774XCGOOEOOUBHY6","created_at":"2026-07-05T04:32:46.322990+00:00"},{"alias_kind":"pith_short_8","alias_value":"774XCGOO","created_at":"2026-07-05T04:32:46.322990+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/774XCGOOEOOUBHY6FDK457BI2T","json":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T.json","graph_json":"https://pith.science/api/pith-number/774XCGOOEOOUBHY6FDK457BI2T/graph.json","events_json":"https://pith.science/api/pith-number/774XCGOOEOOUBHY6FDK457BI2T/events.json","paper":"https://pith.science/paper/774XCGOO"},"agent_actions":{"view_html":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T","download_json":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T.json","view_paper":"https://pith.science/paper/774XCGOO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05672&json=true","fetch_graph":"https://pith.science/api/pith-number/774XCGOOEOOUBHY6FDK457BI2T/graph.json","fetch_events":"https://pith.science/api/pith-number/774XCGOOEOOUBHY6FDK457BI2T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T/action/storage_attestation","attest_author":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T/action/author_attestation","sign_citation":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T/action/citation_signature","submit_replication":"https://pith.science/pith/774XCGOOEOOUBHY6FDK457BI2T/action/replication_record"}},"created_at":"2026-07-05T04:32:46.322990+00:00","updated_at":"2026-07-05T04:32:46.322990+00:00"}