{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:T7DOS3SSRDVGCLOL6OYMCUSQSI","short_pith_number":"pith:T7DOS3SS","schema_version":"1.0","canonical_sha256":"9fc6e96e5288ea612dcbf3b0c1525092293812a18441760f17980ca12b4ac971","source":{"kind":"arxiv","id":"1905.02878","version":1},"attestation_state":"computed","paper":{"title":"Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guohong Fu, Meishan Zhang, Min Zhang, Zhenghua Li","submitted_at":"2019-05-08T02:56:43Z","abstract_excerpt":"Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and Tree-Linearization methods, which may suffer from error propagation. In this work, we propose a novel method to integrate source-side syntax implicitly for NMT. The basic idea is to use the intermediate hidden representations of a well-trained end-to-end dependency parser, which are referred to as syntax-aware word representations (SAWRs). Then, we simply concatenate "},"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":"1905.02878","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T02:56:43Z","cross_cats_sorted":[],"title_canon_sha256":"2f0d06ed2a3c757554d11c30ce5d1c97ed5e2d84102b2b80fb546ffe60707b46","abstract_canon_sha256":"1d80ee0830e2835e649baaf84810330eb8608e353b805fe1ff5798181e5bc5e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:45.118615Z","signature_b64":"XlF/N1vobMo19qOMI8ohhwq4RhAcWDt8ft6soX/qnkTHVjr/Egg/KdELNF8spThWXihSJiriA856YuCThuhQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc6e96e5288ea612dcbf3b0c1525092293812a18441760f17980ca12b4ac971","last_reissued_at":"2026-05-17T23:46:45.118204Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:45.118204Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Guohong Fu, Meishan Zhang, Min Zhang, Zhenghua Li","submitted_at":"2019-05-08T02:56:43Z","abstract_excerpt":"Syntax has been demonstrated highly effective in neural machine translation (NMT). Previous NMT models integrate syntax by representing 1-best tree outputs from a well-trained parsing system, e.g., the representative Tree-RNN and Tree-Linearization methods, which may suffer from error propagation. In this work, we propose a novel method to integrate source-side syntax implicitly for NMT. The basic idea is to use the intermediate hidden representations of a well-trained end-to-end dependency parser, which are referred to as syntax-aware word representations (SAWRs). Then, we simply concatenate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.02878","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":"1905.02878","created_at":"2026-05-17T23:46:45.118269+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.02878v1","created_at":"2026-05-17T23:46:45.118269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.02878","created_at":"2026-05-17T23:46:45.118269+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7DOS3SSRDVG","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7DOS3SSRDVGCLOL","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7DOS3SS","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/T7DOS3SSRDVGCLOL6OYMCUSQSI","json":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI.json","graph_json":"https://pith.science/api/pith-number/T7DOS3SSRDVGCLOL6OYMCUSQSI/graph.json","events_json":"https://pith.science/api/pith-number/T7DOS3SSRDVGCLOL6OYMCUSQSI/events.json","paper":"https://pith.science/paper/T7DOS3SS"},"agent_actions":{"view_html":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI","download_json":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI.json","view_paper":"https://pith.science/paper/T7DOS3SS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.02878&json=true","fetch_graph":"https://pith.science/api/pith-number/T7DOS3SSRDVGCLOL6OYMCUSQSI/graph.json","fetch_events":"https://pith.science/api/pith-number/T7DOS3SSRDVGCLOL6OYMCUSQSI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI/action/storage_attestation","attest_author":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI/action/author_attestation","sign_citation":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI/action/citation_signature","submit_replication":"https://pith.science/pith/T7DOS3SSRDVGCLOL6OYMCUSQSI/action/replication_record"}},"created_at":"2026-05-17T23:46:45.118269+00:00","updated_at":"2026-05-17T23:46:45.118269+00:00"}