{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:QKWEIKD3KP5Y52F6ARG3IEFKPF","short_pith_number":"pith:QKWEIKD3","schema_version":"1.0","canonical_sha256":"82ac44287b53fb8ee8be044db410aa795ae0991f3cd390ccf4c7c8c1cf8a046a","source":{"kind":"arxiv","id":"1908.09532","version":3},"attestation_state":"computed","paper":{"title":"Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Andy Way, Gideon Maillette de Buy Wenniger","submitted_at":"2019-08-26T08:55:00Z","abstract_excerpt":"Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a technique for adapting an NMT model to some domain. In this work, we want to use this technique to adapt the model to a given test set. In particular, we are using transductive data selection algorithms which take advantage the information of the test set to retrieve sentences from a larger parallel set.\n  In cases where the model is available at translation time"},"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":"1908.09532","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-08-26T08:55:00Z","cross_cats_sorted":[],"title_canon_sha256":"c89ec0ca28373bbcfa4f75e1d655215ffb6f9a76a5b9671cefc2e01a018961ba","abstract_canon_sha256":"47694f5158e5190c7368cd9a8f15e6be1e67ded726117e32d4a487f62699206a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:15.677598Z","signature_b64":"5rqaCkMRJSSQI32ACjw0/xfLopNAEk1ryVtRRmXNTrRryYI1cLwchlY/ts7SwW7pHyXYqx7m2OQXY72QE01KBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82ac44287b53fb8ee8be044db410aa795ae0991f3cd390ccf4c7c8c1cf8a046a","last_reissued_at":"2026-07-05T00:10:15.677116Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:15.677116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transductive Data-Selection Algorithms for Fine-Tuning Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Andy Way, Gideon Maillette de Buy Wenniger","submitted_at":"2019-08-26T08:55:00Z","abstract_excerpt":"Machine Translation models are trained to translate a variety of documents from one language into another. However, models specifically trained for a particular characteristics of the documents tend to perform better. Fine-tuning is a technique for adapting an NMT model to some domain. In this work, we want to use this technique to adapt the model to a given test set. In particular, we are using transductive data selection algorithms which take advantage the information of the test set to retrieve sentences from a larger parallel set.\n  In cases where the model is available at translation time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.09532","kind":"arxiv","version":3},"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/1908.09532/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":"1908.09532","created_at":"2026-07-05T00:10:15.677175+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.09532v3","created_at":"2026-07-05T00:10:15.677175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.09532","created_at":"2026-07-05T00:10:15.677175+00:00"},{"alias_kind":"pith_short_12","alias_value":"QKWEIKD3KP5Y","created_at":"2026-07-05T00:10:15.677175+00:00"},{"alias_kind":"pith_short_16","alias_value":"QKWEIKD3KP5Y52F6","created_at":"2026-07-05T00:10:15.677175+00:00"},{"alias_kind":"pith_short_8","alias_value":"QKWEIKD3","created_at":"2026-07-05T00:10:15.677175+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/QKWEIKD3KP5Y52F6ARG3IEFKPF","json":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF.json","graph_json":"https://pith.science/api/pith-number/QKWEIKD3KP5Y52F6ARG3IEFKPF/graph.json","events_json":"https://pith.science/api/pith-number/QKWEIKD3KP5Y52F6ARG3IEFKPF/events.json","paper":"https://pith.science/paper/QKWEIKD3"},"agent_actions":{"view_html":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF","download_json":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF.json","view_paper":"https://pith.science/paper/QKWEIKD3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.09532&json=true","fetch_graph":"https://pith.science/api/pith-number/QKWEIKD3KP5Y52F6ARG3IEFKPF/graph.json","fetch_events":"https://pith.science/api/pith-number/QKWEIKD3KP5Y52F6ARG3IEFKPF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF/action/storage_attestation","attest_author":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF/action/author_attestation","sign_citation":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF/action/citation_signature","submit_replication":"https://pith.science/pith/QKWEIKD3KP5Y52F6ARG3IEFKPF/action/replication_record"}},"created_at":"2026-07-05T00:10:15.677175+00:00","updated_at":"2026-07-05T00:10:15.677175+00:00"}