{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:3XFL6QRKUC46AMHFIYEDST2DVJ","short_pith_number":"pith:3XFL6QRK","schema_version":"1.0","canonical_sha256":"ddcabf422aa0b9e030e54608394f43aa6f91c06affcf11c1f30b60dc0a272e07","source":{"kind":"arxiv","id":"1903.08788","version":2},"attestation_state":"computed","paper":{"title":"Selective Attention for Context-aware Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Gholamreza Haffari, Sameen Maruf","submitted_at":"2019-03-21T01:01:22Z","abstract_excerpt":"Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or w"},"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":"1903.08788","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-21T01:01:22Z","cross_cats_sorted":[],"title_canon_sha256":"680642ef449852ce34e5c162642666407a19bf701ae3e65b40b66c7d88df7494","abstract_canon_sha256":"39a7acd553264fbb0cdd7efd043b540597082be8573e489c6127cc738329cf85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:14.713199Z","signature_b64":"R3IZCZe+F+FrOkNtEGFyAvnEF7zOOlmUTWsc8ZZPwxHK1jJAZEssCJwGqqGaazg5sngkgw2SnWOuNONSsYZuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddcabf422aa0b9e030e54608394f43aa6f91c06affcf11c1f30b60dc0a272e07","last_reissued_at":"2026-05-17T23:45:14.712585Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:14.712585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Selective Attention for Context-aware Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e F. T. Martins, Gholamreza Haffari, Sameen Maruf","submitted_at":"2019-03-21T01:01:22Z","abstract_excerpt":"Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may not scale to entire documents. To this end, we propose a novel and scalable top-down approach to hierarchical attention for context-aware NMT which uses sparse attention to selectively focus on relevant sentences in the document context and then attends to key words in those sentences. We also propose single-level attention approaches based on sentence or w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.08788","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":""},"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":"1903.08788","created_at":"2026-05-17T23:45:14.712704+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.08788v2","created_at":"2026-05-17T23:45:14.712704+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.08788","created_at":"2026-05-17T23:45:14.712704+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XFL6QRKUC46","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XFL6QRKUC46AMHF","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XFL6QRK","created_at":"2026-05-18T12:33:10.108867+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/3XFL6QRKUC46AMHFIYEDST2DVJ","json":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ.json","graph_json":"https://pith.science/api/pith-number/3XFL6QRKUC46AMHFIYEDST2DVJ/graph.json","events_json":"https://pith.science/api/pith-number/3XFL6QRKUC46AMHFIYEDST2DVJ/events.json","paper":"https://pith.science/paper/3XFL6QRK"},"agent_actions":{"view_html":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ","download_json":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ.json","view_paper":"https://pith.science/paper/3XFL6QRK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.08788&json=true","fetch_graph":"https://pith.science/api/pith-number/3XFL6QRKUC46AMHFIYEDST2DVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/3XFL6QRKUC46AMHFIYEDST2DVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ/action/storage_attestation","attest_author":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ/action/author_attestation","sign_citation":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ/action/citation_signature","submit_replication":"https://pith.science/pith/3XFL6QRKUC46AMHFIYEDST2DVJ/action/replication_record"}},"created_at":"2026-05-17T23:45:14.712704+00:00","updated_at":"2026-05-17T23:45:14.712704+00:00"}