{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:NBBJTMQFZ3YRAYUWNCMXRYNHOS","short_pith_number":"pith:NBBJTMQF","schema_version":"1.0","canonical_sha256":"684299b205cef1106296689978e1a774ac478fb4e17e7256f3121d3804e8a2aa","source":{"kind":"arxiv","id":"1707.05436","version":1},"attestation_state":"computed","paper":{"title":"Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Chiang, Huadong Chen, Jiajun Chen, Shujian Huang","submitted_at":"2017-07-18T01:53:58Z","abstract_excerpt":"Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information. In this paper, we improve this model by explicitly incorporating source-side syntactic trees. More specifically, we propose (1) a bidirectional tree encoder which learns both sequential and tree structured representations; (2) a tree-coverage model that lets the attention depend on the source-side syntax. Experiments on Chinese-English translation demonstrate that our proposed models outperform the sequential attentional model as well as a stronger ba"},"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":"1707.05436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-18T01:53:58Z","cross_cats_sorted":[],"title_canon_sha256":"c39d55f71ad0a15867e9e2448579c2e309d6b3aa5ab0b2c2ea2bd44be143463e","abstract_canon_sha256":"2b162fd0c8f36e17a394e0d2298e1546f92ec2f086ae004b59bb9c05cd309aa0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:02.353449Z","signature_b64":"0/4ISVxQ/lk8dzQax6AdQRQH0RPRxwHvPRL9dvvn/ZexjU83fEQ6eZtwoxDQAHEeHA6LSkuO7iAIZBUAYdNmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"684299b205cef1106296689978e1a774ac478fb4e17e7256f3121d3804e8a2aa","last_reissued_at":"2026-05-18T00:40:02.352826Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:02.352826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Neural Machine Translation with a Syntax-Aware Encoder and Decoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Chiang, Huadong Chen, Jiajun Chen, Shujian Huang","submitted_at":"2017-07-18T01:53:58Z","abstract_excerpt":"Most neural machine translation (NMT) models are based on the sequential encoder-decoder framework, which makes no use of syntactic information. In this paper, we improve this model by explicitly incorporating source-side syntactic trees. More specifically, we propose (1) a bidirectional tree encoder which learns both sequential and tree structured representations; (2) a tree-coverage model that lets the attention depend on the source-side syntax. Experiments on Chinese-English translation demonstrate that our proposed models outperform the sequential attentional model as well as a stronger ba"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.05436","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":"1707.05436","created_at":"2026-05-18T00:40:02.352917+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.05436v1","created_at":"2026-05-18T00:40:02.352917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.05436","created_at":"2026-05-18T00:40:02.352917+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBBJTMQFZ3YR","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBBJTMQFZ3YRAYUW","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBBJTMQF","created_at":"2026-05-18T12:31:31.346846+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/NBBJTMQFZ3YRAYUWNCMXRYNHOS","json":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS.json","graph_json":"https://pith.science/api/pith-number/NBBJTMQFZ3YRAYUWNCMXRYNHOS/graph.json","events_json":"https://pith.science/api/pith-number/NBBJTMQFZ3YRAYUWNCMXRYNHOS/events.json","paper":"https://pith.science/paper/NBBJTMQF"},"agent_actions":{"view_html":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS","download_json":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS.json","view_paper":"https://pith.science/paper/NBBJTMQF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.05436&json=true","fetch_graph":"https://pith.science/api/pith-number/NBBJTMQFZ3YRAYUWNCMXRYNHOS/graph.json","fetch_events":"https://pith.science/api/pith-number/NBBJTMQFZ3YRAYUWNCMXRYNHOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS/action/storage_attestation","attest_author":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS/action/author_attestation","sign_citation":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS/action/citation_signature","submit_replication":"https://pith.science/pith/NBBJTMQFZ3YRAYUWNCMXRYNHOS/action/replication_record"}},"created_at":"2026-05-18T00:40:02.352917+00:00","updated_at":"2026-05-18T00:40:02.352917+00:00"}