{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:LUQ4C6U3S3ASSRKZRTPNRIBWUQ","short_pith_number":"pith:LUQ4C6U3","schema_version":"1.0","canonical_sha256":"5d21c17a9b96c12945598cded8a036a433e7647c068844b3ab7e2306c90b250e","source":{"kind":"arxiv","id":"1711.04457","version":1},"attestation_state":"computed","paper":{"title":"Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Jiajun Zhang, Long Zhou, Yining Wang","submitted_at":"2017-11-13T07:42:56Z","abstract_excerpt":"Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabulary problem, but most existing NMT systems operate with a fixed vocabulary, which causes the incapability of translating rare words. This problem can be alleviated by using different translation granularities, such as character, subword and hybrid word-character. Translation involving Chinese is one of the most difficult tasks in machine translation, however, to the best of our"},"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":"1711.04457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-11-13T07:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"d6a01e8be29fe6fdf03238ee23ef4d8e354eb5e3f56f41fdc4a02a7590dcba7d","abstract_canon_sha256":"f72c0babad350defa5dca1e87c8817ffb10891622a2da5c4aba53e97fee97f15"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:38.926961Z","signature_b64":"MKmYxUg8OHrLaNa9gVI4Vfj+/qKFobKaZSY1lC7VPQwRUvQh8mBAEAcPokQNknQjGJSiva5MgyD9Ytp9GPzNDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d21c17a9b96c12945598cded8a036a433e7647c068844b3ab7e2306c90b250e","last_reissued_at":"2026-05-18T00:30:38.926339Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:38.926339Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Word, Subword or Character? An Empirical Study of Granularity in Chinese-English NMT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengqing Zong, Jiajun Zhang, Long Zhou, Yining Wang","submitted_at":"2017-11-13T07:42:56Z","abstract_excerpt":"Neural machine translation (NMT), a new approach to machine translation, has been proved to outperform conventional statistical machine translation (SMT) across a variety of language pairs. Translation is an open-vocabulary problem, but most existing NMT systems operate with a fixed vocabulary, which causes the incapability of translating rare words. This problem can be alleviated by using different translation granularities, such as character, subword and hybrid word-character. Translation involving Chinese is one of the most difficult tasks in machine translation, however, to the best of our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.04457","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":"1711.04457","created_at":"2026-05-18T00:30:38.926437+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.04457v1","created_at":"2026-05-18T00:30:38.926437+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.04457","created_at":"2026-05-18T00:30:38.926437+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUQ4C6U3S3AS","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUQ4C6U3S3ASSRKZ","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUQ4C6U3","created_at":"2026-05-18T12:31:28.150371+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/LUQ4C6U3S3ASSRKZRTPNRIBWUQ","json":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ.json","graph_json":"https://pith.science/api/pith-number/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/graph.json","events_json":"https://pith.science/api/pith-number/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/events.json","paper":"https://pith.science/paper/LUQ4C6U3"},"agent_actions":{"view_html":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ","download_json":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ.json","view_paper":"https://pith.science/paper/LUQ4C6U3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.04457&json=true","fetch_graph":"https://pith.science/api/pith-number/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/action/storage_attestation","attest_author":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/action/author_attestation","sign_citation":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/action/citation_signature","submit_replication":"https://pith.science/pith/LUQ4C6U3S3ASSRKZRTPNRIBWUQ/action/replication_record"}},"created_at":"2026-05-18T00:30:38.926437+00:00","updated_at":"2026-05-18T00:30:38.926437+00:00"}