{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:RLXEQCHHQ7KSS6DMLFK772O3SU","short_pith_number":"pith:RLXEQCHH","schema_version":"1.0","canonical_sha256":"8aee4808e787d529786c5955ffe9db951be72f7422a39ed608bebf4b2eb8f79c","source":{"kind":"arxiv","id":"1907.06170","version":1},"attestation_state":"computed","paper":{"title":"Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcin Junczys-Dowmunt","submitted_at":"2019-07-14T05:47:53Z","abstract_excerpt":"This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parall"},"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":"1907.06170","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-07-14T05:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"49401e9c51a023ca4a7c7a88ff6487f629b4bdee0c344b87c3cb7075a49040a7","abstract_canon_sha256":"d621ffe4632d474ad089ddd9321c3197395189ef83d8442a99144c025d87f43e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:38.319294Z","signature_b64":"4l4GbLcpk2kaYiulYmi56r1lycytJyyboSMN7GKYDBzNCaP8ysh+GUOQPRa7I8bfb+jTPKcr5Z4TYy0zkjgWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aee4808e787d529786c5955ffe9db951be72f7422a39ed608bebf4b2eb8f79c","last_reissued_at":"2026-05-17T23:40:38.318724Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:38.318724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Microsoft Translator at WMT 2019: Towards Large-Scale Document-Level Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcin Junczys-Dowmunt","submitted_at":"2019-07-14T05:47:53Z","abstract_excerpt":"This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong sentence-level baselines, trained on large-scale data created via data-filtering and noisy back-translation and find that back-translation seems to mainly help with translationese input. We explore fine-tuning techniques, deeper models and different ensembling strategies to counter these effects. Using document boundaries present in the authentic and synthetic parall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06170","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":""},"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":"1907.06170","created_at":"2026-05-17T23:40:38.318804+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.06170v1","created_at":"2026-05-17T23:40:38.318804+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06170","created_at":"2026-05-17T23:40:38.318804+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLXEQCHHQ7KS","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLXEQCHHQ7KSS6DM","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLXEQCHH","created_at":"2026-05-18T12:33:27.125529+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/RLXEQCHHQ7KSS6DMLFK772O3SU","json":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU.json","graph_json":"https://pith.science/api/pith-number/RLXEQCHHQ7KSS6DMLFK772O3SU/graph.json","events_json":"https://pith.science/api/pith-number/RLXEQCHHQ7KSS6DMLFK772O3SU/events.json","paper":"https://pith.science/paper/RLXEQCHH"},"agent_actions":{"view_html":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU","download_json":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU.json","view_paper":"https://pith.science/paper/RLXEQCHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.06170&json=true","fetch_graph":"https://pith.science/api/pith-number/RLXEQCHHQ7KSS6DMLFK772O3SU/graph.json","fetch_events":"https://pith.science/api/pith-number/RLXEQCHHQ7KSS6DMLFK772O3SU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU/action/storage_attestation","attest_author":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU/action/author_attestation","sign_citation":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU/action/citation_signature","submit_replication":"https://pith.science/pith/RLXEQCHHQ7KSS6DMLFK772O3SU/action/replication_record"}},"created_at":"2026-05-17T23:40:38.318804+00:00","updated_at":"2026-05-17T23:40:38.318804+00:00"}