{"id":"W4416655590","doi":"10.1080/0907676x.2025.2590066","title":"Measuring lexical distance between parallel corpora: the case of AI-generated news translation","year":2025,"lang":"en","type":"article","venue":"Perspectives","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Translation (biology); Machine translation; Feature (linguistics); Measure (data warehouse); Lexical item","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001987704,0.0001014869,0.0001475489,0.00007893034,0.0001517711,0.000084306,0.0004646503,0.00005143265,0.000002088408],"category_scores_gemma":[0.00007246242,0.00007079196,0.00005487151,0.0005607819,0.0001177024,0.0002849798,0.00006700539,0.0002070966,7.347138e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005523647,"about_ca_system_score_gemma":0.0000721564,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002479493,"about_ca_topic_score_gemma":0.0001374524,"domain_scores_codex":[0.9992151,0.00009481973,0.0001720539,0.0002736407,0.000114087,0.0001302526],"domain_scores_gemma":[0.9993125,0.0001144476,0.00007488012,0.0003188661,0.000155622,0.00002364227],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002818117,0.00006821028,0.002669252,0.00005094081,0.0000699598,0.0001022843,0.01019782,0.00006371622,0.003637747,0.8456173,0.0003103517,0.1371842],"study_design_scores_gemma":[0.001180609,0.0001680605,0.005255203,0.0003341781,0.0001132401,0.0001393992,0.004487636,0.04435007,0.1111222,0.8309852,0.00106865,0.0007955263],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01209408,0.008492923,0.9734696,0.00468538,0.00004602804,0.0001614861,0.000003690736,0.0002249601,0.000821867],"genre_scores_gemma":[0.8820029,0.00001460032,0.1178156,0.0000591747,0.00003526375,0.00001014353,9.576138e-7,0.000003906834,0.00005749861],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8699088,"threshold_uncertainty_score":0.2886812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04217812593225261,"score_gpt":0.3094155154243002,"score_spread":0.2672373894920476,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}