{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VVAWRVDUFV33BY6TLIQRWTKZD7","short_pith_number":"pith:VVAWRVDU","schema_version":"1.0","canonical_sha256":"ad4168d4742d77b0e3d35a211b4d591fcc4389e36bff7c9808155bab80096469","source":{"kind":"arxiv","id":"2306.12089","version":1},"attestation_state":"computed","paper":{"title":"Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"(2) Korea University, (3) Papago, Cheonbok Park (3), Dayeon Ki (2), Hyoung-Gyu Lee (3), Jaegul Choo (1) ((1) KAIST, Koanho Lee (1), Naver Corp.), Yujin Baek (1)","submitted_at":"2023-06-21T08:08:15Z","abstract_excerpt":"Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but under-studied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are \"homographs\" or \"unseen\" during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT, which i"},"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":"2306.12089","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-21T08:08:15Z","cross_cats_sorted":[],"title_canon_sha256":"68848d45f55a48c5ea82f4d17c94b1eb4d0fb2aa3a548f9206de070dc8d43942","abstract_canon_sha256":"47d082acd9f493b364c370b698bd3b642c3ff9b9bd36b0913547c1d0af1ad39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:10.472164Z","signature_b64":"7UoHuLtY4cdzNNoGbp2C5QtUvNbNXb7Nu9bpeeKPbTjlRzfA6CiBRCjsKC35b8Gnd2IITlsEjoAXqO3p2uKHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ad4168d4742d77b0e3d35a211b4d591fcc4389e36bff7c9808155bab80096469","last_reissued_at":"2026-07-05T06:23:10.471827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:10.471827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"(2) Korea University, (3) Papago, Cheonbok Park (3), Dayeon Ki (2), Hyoung-Gyu Lee (3), Jaegul Choo (1) ((1) KAIST, Koanho Lee (1), Naver Corp.), Yujin Baek (1)","submitted_at":"2023-06-21T08:08:15Z","abstract_excerpt":"Lexically-constrained NMT (LNMT) aims to incorporate user-provided terminology into translations. Despite its practical advantages, existing work has not evaluated LNMT models under challenging real-world conditions. In this paper, we focus on two important but under-studied issues that lie in the current evaluation process of LNMT studies. The model needs to cope with challenging lexical constraints that are \"homographs\" or \"unseen\" during training. To this end, we first design a homograph disambiguation module to differentiate the meanings of homographs. Moreover, we propose PLUMCOT, which i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12089","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/2306.12089/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":"2306.12089","created_at":"2026-07-05T06:23:10.471880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12089v1","created_at":"2026-07-05T06:23:10.471880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12089","created_at":"2026-07-05T06:23:10.471880+00:00"},{"alias_kind":"pith_short_12","alias_value":"VVAWRVDUFV33","created_at":"2026-07-05T06:23:10.471880+00:00"},{"alias_kind":"pith_short_16","alias_value":"VVAWRVDUFV33BY6T","created_at":"2026-07-05T06:23:10.471880+00:00"},{"alias_kind":"pith_short_8","alias_value":"VVAWRVDU","created_at":"2026-07-05T06:23:10.471880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.16601","citing_title":"Comparing Large Language Models and Traditional Machine Translation Tools for Translating Medical Consultation Summaries: A Pilot Study","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7","json":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7.json","graph_json":"https://pith.science/api/pith-number/VVAWRVDUFV33BY6TLIQRWTKZD7/graph.json","events_json":"https://pith.science/api/pith-number/VVAWRVDUFV33BY6TLIQRWTKZD7/events.json","paper":"https://pith.science/paper/VVAWRVDU"},"agent_actions":{"view_html":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7","download_json":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7.json","view_paper":"https://pith.science/paper/VVAWRVDU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12089&json=true","fetch_graph":"https://pith.science/api/pith-number/VVAWRVDUFV33BY6TLIQRWTKZD7/graph.json","fetch_events":"https://pith.science/api/pith-number/VVAWRVDUFV33BY6TLIQRWTKZD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7/action/storage_attestation","attest_author":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7/action/author_attestation","sign_citation":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7/action/citation_signature","submit_replication":"https://pith.science/pith/VVAWRVDUFV33BY6TLIQRWTKZD7/action/replication_record"}},"created_at":"2026-07-05T06:23:10.471880+00:00","updated_at":"2026-07-05T06:23:10.471880+00:00"}