{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HF45UODRAFII4AG67YH53CXYOS","short_pith_number":"pith:HF45UODR","schema_version":"1.0","canonical_sha256":"3979da387101508e00defe0fdd8af874a24c384c3c119b27c64ffd5eb5dd2a8e","source":{"kind":"arxiv","id":"2105.14878","version":2},"attestation_state":"computed","paper":{"title":"Verdi: Quality Estimation and Error Detection for Bilingual Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Niu, Haijiang Wu, Mingjun Zhao, Xiaoli Wang, Zixuan Wang","submitted_at":"2021-05-31T11:04:13Z","abstract_excerpt":"Translation Quality Estimation is critical to reducing post-editing efforts in machine translation and to cross-lingual corpus cleaning. As a research problem, quality estimation (QE) aims to directly estimate the quality of translation in a given pair of source and target sentences, and highlight the words that need corrections, without referencing to golden translations. In this paper, we propose Verdi, a novel framework for word-level and sentence-level post-editing effort estimation for bilingual corpora. Verdi adopts two word predictors to enable diverse features to be extracted from a pa"},"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":"2105.14878","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-31T11:04:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e510bab588edbda1c6b43539d7955c8c632eb5f831971b0292ddc7a74ca8d002","abstract_canon_sha256":"f8fbe08a39c74e181019cf099227fbcf278d2f313452a2127c35596779f5989c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:13.036956Z","signature_b64":"4IuJQ5LWm9yr8hCEBbnZdNvdlKfGtICPyOV7RXzLZ23dhDnBkDJ+M95+huRaBzwt1YDNtPn1eIgseHGDRRRHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3979da387101508e00defe0fdd8af874a24c384c3c119b27c64ffd5eb5dd2a8e","last_reissued_at":"2026-07-05T03:11:13.036472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:13.036472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Verdi: Quality Estimation and Error Detection for Bilingual Corpora","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Niu, Haijiang Wu, Mingjun Zhao, Xiaoli Wang, Zixuan Wang","submitted_at":"2021-05-31T11:04:13Z","abstract_excerpt":"Translation Quality Estimation is critical to reducing post-editing efforts in machine translation and to cross-lingual corpus cleaning. As a research problem, quality estimation (QE) aims to directly estimate the quality of translation in a given pair of source and target sentences, and highlight the words that need corrections, without referencing to golden translations. In this paper, we propose Verdi, a novel framework for word-level and sentence-level post-editing effort estimation for bilingual corpora. Verdi adopts two word predictors to enable diverse features to be extracted from a pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.14878","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/2105.14878/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":"2105.14878","created_at":"2026-07-05T03:11:13.036525+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.14878v2","created_at":"2026-07-05T03:11:13.036525+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.14878","created_at":"2026-07-05T03:11:13.036525+00:00"},{"alias_kind":"pith_short_12","alias_value":"HF45UODRAFII","created_at":"2026-07-05T03:11:13.036525+00:00"},{"alias_kind":"pith_short_16","alias_value":"HF45UODRAFII4AG6","created_at":"2026-07-05T03:11:13.036525+00:00"},{"alias_kind":"pith_short_8","alias_value":"HF45UODR","created_at":"2026-07-05T03:11:13.036525+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/HF45UODRAFII4AG67YH53CXYOS","json":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS.json","graph_json":"https://pith.science/api/pith-number/HF45UODRAFII4AG67YH53CXYOS/graph.json","events_json":"https://pith.science/api/pith-number/HF45UODRAFII4AG67YH53CXYOS/events.json","paper":"https://pith.science/paper/HF45UODR"},"agent_actions":{"view_html":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS","download_json":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS.json","view_paper":"https://pith.science/paper/HF45UODR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.14878&json=true","fetch_graph":"https://pith.science/api/pith-number/HF45UODRAFII4AG67YH53CXYOS/graph.json","fetch_events":"https://pith.science/api/pith-number/HF45UODRAFII4AG67YH53CXYOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS/action/storage_attestation","attest_author":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS/action/author_attestation","sign_citation":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS/action/citation_signature","submit_replication":"https://pith.science/pith/HF45UODRAFII4AG67YH53CXYOS/action/replication_record"}},"created_at":"2026-07-05T03:11:13.036525+00:00","updated_at":"2026-07-05T03:11:13.036525+00:00"}