{"id":"W7132432999","doi":"","title":"Translation memories as baselines for low-resource machine translation","year":2022,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Machine translation; Example-based machine translation; Translation (biology); Machine translation software usability; Baseline (sea); Benchmark (surveying); Computer-assisted translation","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01037602,0.001076125,0.001092935,0.003137225,0.001651941,0.003206977,0.002511387,0.0019576,0.007585234],"category_scores_gemma":[0.0542002,0.0005820165,0.0006713286,0.003470316,0.001483591,0.007532658,0.003037926,0.002410435,0.004080087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00127113,"about_ca_system_score_gemma":0.001014195,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001499821,"about_ca_topic_score_gemma":0.002796917,"domain_scores_codex":[0.990056,0.005760751,0.000878322,0.001582323,0.001402993,0.0003196692],"domain_scores_gemma":[0.9730304,0.01455287,0.001728149,0.006887208,0.003390499,0.0004108688],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.006039845,0.001315321,0.00948375,0.002191819,0.0009396912,0.0004383656,0.001445472,0.1021448,0.03469377,0.05752328,0.03820707,0.7455768],"study_design_scores_gemma":[0.001084285,0.004651052,0.01420801,0.0006732747,0.001004789,0.0009081903,0.001680237,0.5543727,0.1406741,0.1934442,0.0869249,0.0003743166],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.33783,0.01352779,0.5720881,0.002330497,0.001940947,0.001183466,0.008463682,0.01917146,0.04346418],"genre_scores_gemma":[0.7716276,0.0009249676,0.206502,0.00057833,0.0003816634,0.001369828,0.01093696,0.001769887,0.005908779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01037602,"threshold_uncertainty_score":0.0548743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01731235593691944,"score_gpt":0.272225155085102,"score_spread":0.2549127991481826,"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."}}