{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:RXEX66QZOBTE3F5RXBZ2PI44AW","short_pith_number":"pith:RXEX66QZ","schema_version":"1.0","canonical_sha256":"8dc97f7a1970664d97b1b873a7a39c05a17d394b28e1c5fe44a137c05d5acfb2","source":{"kind":"arxiv","id":"2205.11255","version":2},"attestation_state":"computed","paper":{"title":"A Template-based Method for Constrained Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Peng Li, Shuo Wang, Yang Liu, Zhaopeng Tu, Zhixing Tan","submitted_at":"2022-05-23T12:24:34Z","abstract_excerpt":"Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield r"},"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":"2205.11255","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-23T12:24:34Z","cross_cats_sorted":[],"title_canon_sha256":"3358c3b48454b2c0f482fe2283c5f280c9263e783a6a6cce5c03866aae8a8903","abstract_canon_sha256":"0ee465ce0089eb1b957ea3212b6350f22ba00c95fb9aa8cb3f1437f0f2d886cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:52.017630Z","signature_b64":"L8kLKyPIYb2+jz/Bj5LhjB9wPipcPe8ZEAGxF4P9fqhsQE+oPy777FxVE1T2r1Vn5+LztEikosCEBeQLM6heAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc97f7a1970664d97b1b873a7a39c05a17d394b28e1c5fe44a137c05d5acfb2","last_reissued_at":"2026-07-05T05:08:52.017079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:52.017079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Template-based Method for Constrained Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maosong Sun, Peng Li, Shuo Wang, Yang Liu, Zhaopeng Tu, Zhixing Tan","submitted_at":"2022-05-23T12:24:34Z","abstract_excerpt":"Machine translation systems are expected to cope with various types of constraints in many practical scenarios. While neural machine translation (NMT) has achieved strong performance in unconstrained cases, it is non-trivial to impose pre-specified constraints into the translation process of NMT models. Although many approaches have been proposed to address this issue, most existing methods can not satisfy the following three desiderata at the same time: (1) high translation quality, (2) high match accuracy, and (3) low latency. In this work, we propose a template-based method that can yield r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11255","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2205.11255/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":"2205.11255","created_at":"2026-07-05T05:08:52.017152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11255v2","created_at":"2026-07-05T05:08:52.017152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11255","created_at":"2026-07-05T05:08:52.017152+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXEX66QZOBTE","created_at":"2026-07-05T05:08:52.017152+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXEX66QZOBTE3F5R","created_at":"2026-07-05T05:08:52.017152+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXEX66QZ","created_at":"2026-07-05T05:08:52.017152+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/RXEX66QZOBTE3F5RXBZ2PI44AW","json":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW.json","graph_json":"https://pith.science/api/pith-number/RXEX66QZOBTE3F5RXBZ2PI44AW/graph.json","events_json":"https://pith.science/api/pith-number/RXEX66QZOBTE3F5RXBZ2PI44AW/events.json","paper":"https://pith.science/paper/RXEX66QZ"},"agent_actions":{"view_html":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW","download_json":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW.json","view_paper":"https://pith.science/paper/RXEX66QZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11255&json=true","fetch_graph":"https://pith.science/api/pith-number/RXEX66QZOBTE3F5RXBZ2PI44AW/graph.json","fetch_events":"https://pith.science/api/pith-number/RXEX66QZOBTE3F5RXBZ2PI44AW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW/action/storage_attestation","attest_author":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW/action/author_attestation","sign_citation":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW/action/citation_signature","submit_replication":"https://pith.science/pith/RXEX66QZOBTE3F5RXBZ2PI44AW/action/replication_record"}},"created_at":"2026-07-05T05:08:52.017152+00:00","updated_at":"2026-07-05T05:08:52.017152+00:00"}