{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:EEQUTUWN3MSWEVSANY6KLOQN77","short_pith_number":"pith:EEQUTUWN","schema_version":"1.0","canonical_sha256":"212149d2cddb256256406e3ca5ba0dfffe6d45a7fe0cabe2f178b348e95830f4","source":{"kind":"arxiv","id":"1910.07481","version":1},"attestation_state":"computed","paper":{"title":"Using Whole Document Context in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christophe Servan, Valentin Mac\\'e","submitted_at":"2019-10-16T17:15:35Z","abstract_excerpt":"In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We present a method to add source context that capture the whole document with accurate boundaries, taking every word into account. We provide this additional information to a Transformer model and study the impact of our method on three language pairs. The proposed approach obtains promising results in the English-German, English-French and French-English document-"},"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":"1910.07481","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-16T17:15:35Z","cross_cats_sorted":[],"title_canon_sha256":"64eeaa35c83b4175deb0555ed44bb20202cbd766fd7316140133fafc0b7595e1","abstract_canon_sha256":"942e25e59b07ee699ed49869b4f94c185f519cb911760779dfe44e27dea4d95d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:12:36.365817Z","signature_b64":"xf5BaCj+Ycdzrxn3E7Aq9yrd79qjPzvDMHHGJn6+gP7fvhFHw4Rgk3IptoLrBx4eGLlNT4pzIDOJrMMY/1hqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"212149d2cddb256256406e3ca5ba0dfffe6d45a7fe0cabe2f178b348e95830f4","last_reissued_at":"2026-07-05T00:12:36.365428Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:12:36.365428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Whole Document Context in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christophe Servan, Valentin Mac\\'e","submitted_at":"2019-10-16T17:15:35Z","abstract_excerpt":"In Machine Translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a simple yet promising approach to add contextual information in Neural Machine Translation. We present a method to add source context that capture the whole document with accurate boundaries, taking every word into account. We provide this additional information to a Transformer model and study the impact of our method on three language pairs. The proposed approach obtains promising results in the English-German, English-French and French-English document-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.07481","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1910.07481/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":"1910.07481","created_at":"2026-07-05T00:12:36.365481+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.07481v1","created_at":"2026-07-05T00:12:36.365481+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.07481","created_at":"2026-07-05T00:12:36.365481+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEQUTUWN3MSW","created_at":"2026-07-05T00:12:36.365481+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEQUTUWN3MSWEVSA","created_at":"2026-07-05T00:12:36.365481+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEQUTUWN","created_at":"2026-07-05T00:12:36.365481+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/EEQUTUWN3MSWEVSANY6KLOQN77","json":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77.json","graph_json":"https://pith.science/api/pith-number/EEQUTUWN3MSWEVSANY6KLOQN77/graph.json","events_json":"https://pith.science/api/pith-number/EEQUTUWN3MSWEVSANY6KLOQN77/events.json","paper":"https://pith.science/paper/EEQUTUWN"},"agent_actions":{"view_html":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77","download_json":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77.json","view_paper":"https://pith.science/paper/EEQUTUWN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.07481&json=true","fetch_graph":"https://pith.science/api/pith-number/EEQUTUWN3MSWEVSANY6KLOQN77/graph.json","fetch_events":"https://pith.science/api/pith-number/EEQUTUWN3MSWEVSANY6KLOQN77/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77/action/storage_attestation","attest_author":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77/action/author_attestation","sign_citation":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77/action/citation_signature","submit_replication":"https://pith.science/pith/EEQUTUWN3MSWEVSANY6KLOQN77/action/replication_record"}},"created_at":"2026-07-05T00:12:36.365481+00:00","updated_at":"2026-07-05T00:12:36.365481+00:00"}