{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2DZ56SGO4DKTLC5RNN3M7TZ45N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6149f3cf7e439066d792dd96b0052d69bc363f8acf498992434ca7fe507187ef","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-17T08:13:36Z","title_canon_sha256":"01147fbc80f507fc0b37194d15fae49507a72b92d840dd67de4b217c97307ad6"},"schema_version":"1.0","source":{"id":"2002.06823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06823","created_at":"2026-07-05T00:41:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06823v1","created_at":"2026-07-05T00:41:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06823","created_at":"2026-07-05T00:41:09Z"},{"alias_kind":"pith_short_12","alias_value":"2DZ56SGO4DKT","created_at":"2026-07-05T00:41:09Z"},{"alias_kind":"pith_short_16","alias_value":"2DZ56SGO4DKTLC5R","created_at":"2026-07-05T00:41:09Z"},{"alias_kind":"pith_short_8","alias_value":"2DZ56SGO","created_at":"2026-07-05T00:41:09Z"}],"graph_snapshots":[{"event_id":"sha256:db84a0ccee46f06ddb83649938e94ab86ad1441f82f63bf859963facae22e136","target":"graph","created_at":"2026-07-05T00:41:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.06823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks enough exploration. While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using for fine-tuning. This motivates us to think how to better leverage BERT for NMT along this direction. We propose a new ","authors_text":"Di He, Houqiang Li, Jinhua Zhu, Lijun Wu, Tao Qin, Tie-Yan Liu, Wengang Zhou, Yingce Xia","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-17T08:13:36Z","title":"Incorporating BERT into Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06823","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8e150200682bbbca6315c7caece094a1295f7f48e3681bd858fd9a7ddbad51c5","target":"record","created_at":"2026-07-05T00:41:09Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6149f3cf7e439066d792dd96b0052d69bc363f8acf498992434ca7fe507187ef","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-17T08:13:36Z","title_canon_sha256":"01147fbc80f507fc0b37194d15fae49507a72b92d840dd67de4b217c97307ad6"},"schema_version":"1.0","source":{"id":"2002.06823","kind":"arxiv","version":1}},"canonical_sha256":"d0f3df48cee0d5358bb16b76cfcf3ceb490ec1e6a58c891b15d5882f0ac0e077","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0f3df48cee0d5358bb16b76cfcf3ceb490ec1e6a58c891b15d5882f0ac0e077","first_computed_at":"2026-07-05T00:41:09.535780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:41:09.535780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J9+qrjfd6sLzM1SfdNOz11EfK5vWvvhV255XLfich2tYtyAJ1TitdQ0foG8gg9wXxqYYplsEHJKEDIUyx6iIBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:41:09.536209Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e150200682bbbca6315c7caece094a1295f7f48e3681bd858fd9a7ddbad51c5","sha256:db84a0ccee46f06ddb83649938e94ab86ad1441f82f63bf859963facae22e136"],"state_sha256":"cf8598b5001bedafdfcc1388777dc4cef78d250c6eafa6d56f9f3f5d11939158"}