{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7TIPM3NZTUFIAJP4OYUNZ52PIW","short_pith_number":"pith:7TIPM3NZ","schema_version":"1.0","canonical_sha256":"fcd0f66db99d0a8025fc7628dcf74f45866bc09e653370e3e9598b151ff2dbce","source":{"kind":"arxiv","id":"2309.13230","version":4},"attestation_state":"computed","paper":{"title":"Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiajun Chen, Shimin Tao, Shujian Huang, Xiang Geng, Yu Zhang, Zhejian Lai","submitted_at":"2023-09-23T01:52:14Z","abstract_excerpt":"We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) fine-grained error span detection. This year, we further explore pseudo data methods for QE based on NJUQE framework (https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using parallel data from the WMT translation task. We pre-train the XLMR large model on pseudo QE data, then fine-tune it on real QE data. At both stages, we jointly learn"},"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":"2309.13230","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-23T01:52:14Z","cross_cats_sorted":[],"title_canon_sha256":"7f5fa78cc770e38e1cc82fa07f25688f1153b1b4dc831440d5c138961f68159a","abstract_canon_sha256":"6eadd00846bff0645ac5ea599542728c2b18c08f55b8f6b741b47f0ed0b84667"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:23.479233Z","signature_b64":"GQjb8RZ3k9Mz3P9i+uf2JilPuRLkwUQYRzIu78yEfzsjlqQ0UVc2vzFECWU8ORah4zbjd5nY1cWnlWiP84ulCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcd0f66db99d0a8025fc7628dcf74f45866bc09e653370e3e9598b151ff2dbce","last_reissued_at":"2026-07-05T07:22:23.478759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:23.478759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hao Yang, Jiajun Chen, Shimin Tao, Shujian Huang, Xiang Geng, Yu Zhang, Zhejian Lai","submitted_at":"2023-09-23T01:52:14Z","abstract_excerpt":"We introduce the submissions of the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks: (i) sentence- and word-level quality prediction; and (ii) fine-grained error span detection. This year, we further explore pseudo data methods for QE based on NJUQE framework (https://github.com/NJUNLP/njuqe). We generate pseudo MQM data using parallel data from the WMT translation task. We pre-train the XLMR large model on pseudo QE data, then fine-tune it on real QE data. At both stages, we jointly learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13230","kind":"arxiv","version":4},"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/2309.13230/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":"2309.13230","created_at":"2026-07-05T07:22:23.478813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13230v4","created_at":"2026-07-05T07:22:23.478813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13230","created_at":"2026-07-05T07:22:23.478813+00:00"},{"alias_kind":"pith_short_12","alias_value":"7TIPM3NZTUFI","created_at":"2026-07-05T07:22:23.478813+00:00"},{"alias_kind":"pith_short_16","alias_value":"7TIPM3NZTUFIAJP4","created_at":"2026-07-05T07:22:23.478813+00:00"},{"alias_kind":"pith_short_8","alias_value":"7TIPM3NZ","created_at":"2026-07-05T07:22:23.478813+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/7TIPM3NZTUFIAJP4OYUNZ52PIW","json":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW.json","graph_json":"https://pith.science/api/pith-number/7TIPM3NZTUFIAJP4OYUNZ52PIW/graph.json","events_json":"https://pith.science/api/pith-number/7TIPM3NZTUFIAJP4OYUNZ52PIW/events.json","paper":"https://pith.science/paper/7TIPM3NZ"},"agent_actions":{"view_html":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW","download_json":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW.json","view_paper":"https://pith.science/paper/7TIPM3NZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13230&json=true","fetch_graph":"https://pith.science/api/pith-number/7TIPM3NZTUFIAJP4OYUNZ52PIW/graph.json","fetch_events":"https://pith.science/api/pith-number/7TIPM3NZTUFIAJP4OYUNZ52PIW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW/action/storage_attestation","attest_author":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW/action/author_attestation","sign_citation":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW/action/citation_signature","submit_replication":"https://pith.science/pith/7TIPM3NZTUFIAJP4OYUNZ52PIW/action/replication_record"}},"created_at":"2026-07-05T07:22:23.478813+00:00","updated_at":"2026-07-05T07:22:23.478813+00:00"}