{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6WVSNCQSRDAQFQXMD5CDNZP57O","short_pith_number":"pith:6WVSNCQS","schema_version":"1.0","canonical_sha256":"f5ab268a1288c102c2ec1f4436e5fdfbb40a444058afc9dd50621cb15359044a","source":{"kind":"arxiv","id":"2109.09991","version":2},"attestation_state":"computed","paper":{"title":"Learning Kernel-Smoothed Machine Translation with Retrieved Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Cao, Lei Li, Mingxuan Wang, Qingnan Jiang, Shanbo Cheng, Shujian Huang","submitted_at":"2021-09-21T06:42:53Z","abstract_excerpt":"How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples. In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. Experiments on domain adapta"},"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":"2109.09991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-21T06:42:53Z","cross_cats_sorted":[],"title_canon_sha256":"4190e4b752fe23efb58ca87a6d2ae58e15b07e0718a11e22429876c7bbd796a0","abstract_canon_sha256":"9c518aadf85a7dbfb4445b36a70752602fd0e02ecf2214d7cd033c6acdf4a400"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:03.369087Z","signature_b64":"mFyTK41FMyAgUt62LKexTLXAxQJ91HEPAUTOqpS+HkG9aOOcVYYFU+a6vUaTYyti9Ywzhqzi+vH8XA4CrMG4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5ab268a1288c102c2ec1f4436e5fdfbb40a444058afc9dd50621cb15359044a","last_reissued_at":"2026-07-05T03:39:03.368574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:03.368574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Kernel-Smoothed Machine Translation with Retrieved Examples","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jun Cao, Lei Li, Mingxuan Wang, Qingnan Jiang, Shanbo Cheng, Shujian Huang","submitted_at":"2021-09-21T06:42:53Z","abstract_excerpt":"How to effectively adapt neural machine translation (NMT) models according to emerging cases without retraining? Despite the great success of neural machine translation, updating the deployed models online remains a challenge. Existing non-parametric approaches that retrieve similar examples from a database to guide the translation process are promising but are prone to overfit the retrieved examples. In this work, we propose to learn Kernel-Smoothed Translation with Example Retrieval (KSTER), an effective approach to adapt neural machine translation models online. Experiments on domain adapta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09991","kind":"arxiv","version":2},"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/2109.09991/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":"2109.09991","created_at":"2026-07-05T03:39:03.368633+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09991v2","created_at":"2026-07-05T03:39:03.368633+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09991","created_at":"2026-07-05T03:39:03.368633+00:00"},{"alias_kind":"pith_short_12","alias_value":"6WVSNCQSRDAQ","created_at":"2026-07-05T03:39:03.368633+00:00"},{"alias_kind":"pith_short_16","alias_value":"6WVSNCQSRDAQFQXM","created_at":"2026-07-05T03:39:03.368633+00:00"},{"alias_kind":"pith_short_8","alias_value":"6WVSNCQS","created_at":"2026-07-05T03:39:03.368633+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/6WVSNCQSRDAQFQXMD5CDNZP57O","json":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O.json","graph_json":"https://pith.science/api/pith-number/6WVSNCQSRDAQFQXMD5CDNZP57O/graph.json","events_json":"https://pith.science/api/pith-number/6WVSNCQSRDAQFQXMD5CDNZP57O/events.json","paper":"https://pith.science/paper/6WVSNCQS"},"agent_actions":{"view_html":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O","download_json":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O.json","view_paper":"https://pith.science/paper/6WVSNCQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09991&json=true","fetch_graph":"https://pith.science/api/pith-number/6WVSNCQSRDAQFQXMD5CDNZP57O/graph.json","fetch_events":"https://pith.science/api/pith-number/6WVSNCQSRDAQFQXMD5CDNZP57O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O/action/storage_attestation","attest_author":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O/action/author_attestation","sign_citation":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O/action/citation_signature","submit_replication":"https://pith.science/pith/6WVSNCQSRDAQFQXMD5CDNZP57O/action/replication_record"}},"created_at":"2026-07-05T03:39:03.368633+00:00","updated_at":"2026-07-05T03:39:03.368633+00:00"}