{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:KL2E5DUJTQPKBJFXZ4DAV2GGIJ","short_pith_number":"pith:KL2E5DUJ","schema_version":"1.0","canonical_sha256":"52f44e8e899c1ea0a4b7cf060ae8c6425ed0f61e7931a97c8d5b4fe7fae0045f","source":{"kind":"arxiv","id":"2004.12681","version":1},"attestation_state":"computed","paper":{"title":"Lexically Constrained Neural Machine Translation with Levenshtein Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liling Tan, Raymond Hendy Susanto, Shamil Chollampatt","submitted_at":"2020-04-27T09:59:27Z","abstract_excerpt":"This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be "},"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":"2004.12681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-27T09:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"cce1337dfea18b8cf7688f40e8564528823fd67e1646c9a8aa4aa6c514e31165","abstract_canon_sha256":"ca943d68f40568f75bb00508d340e6e403329127d2566167e63525f2e90a93d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:17.563373Z","signature_b64":"+VdrAgZnuk3o4jsGFojB0NgtlpSFWAR/kHmMpPS/DTpO0vSMmggcdUiQiEiQ/eU45XwTKJuSdUAFlrIJQ9vYAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f44e8e899c1ea0a4b7cf060ae8c6425ed0f61e7931a97c8d5b4fe7fae0045f","last_reissued_at":"2026-07-05T00:58:17.562937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:17.562937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lexically Constrained Neural Machine Translation with Levenshtein Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Liling Tan, Raymond Hendy Susanto, Shamil Chollampatt","submitted_at":"2020-04-27T09:59:27Z","abstract_excerpt":"This paper proposes a simple and effective algorithm for incorporating lexical constraints in neural machine translation. Previous work either required re-training existing models with the lexical constraints or incorporating them during beam search decoding with significantly higher computational overheads. Leveraging the flexibility and speed of a recently proposed Levenshtein Transformer model (Gu et al., 2019), our method injects terminology constraints at inference time without any impact on decoding speed. Our method does not require any modification to the training procedure and can be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12681","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2004.12681/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":"2004.12681","created_at":"2026-07-05T00:58:17.562994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.12681v1","created_at":"2026-07-05T00:58:17.562994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12681","created_at":"2026-07-05T00:58:17.562994+00:00"},{"alias_kind":"pith_short_12","alias_value":"KL2E5DUJTQPK","created_at":"2026-07-05T00:58:17.562994+00:00"},{"alias_kind":"pith_short_16","alias_value":"KL2E5DUJTQPKBJFX","created_at":"2026-07-05T00:58:17.562994+00:00"},{"alias_kind":"pith_short_8","alias_value":"KL2E5DUJ","created_at":"2026-07-05T00:58:17.562994+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05569","citing_title":"SMI-Editor: Edit-based SMILES Language Model with Fragment-level Supervision","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ","json":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ.json","graph_json":"https://pith.science/api/pith-number/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/graph.json","events_json":"https://pith.science/api/pith-number/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/events.json","paper":"https://pith.science/paper/KL2E5DUJ"},"agent_actions":{"view_html":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ","download_json":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ.json","view_paper":"https://pith.science/paper/KL2E5DUJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.12681&json=true","fetch_graph":"https://pith.science/api/pith-number/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/graph.json","fetch_events":"https://pith.science/api/pith-number/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/action/storage_attestation","attest_author":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/action/author_attestation","sign_citation":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/action/citation_signature","submit_replication":"https://pith.science/pith/KL2E5DUJTQPKBJFXZ4DAV2GGIJ/action/replication_record"}},"created_at":"2026-07-05T00:58:17.562994+00:00","updated_at":"2026-07-05T00:58:17.562994+00:00"}