{"id":"W1967963033","doi":"10.7202/1006182ar","title":"Dutch Parallel Corpus: A Balanced Copyright-Cleared Parallel Corpus","year":2011,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":77,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Parallel corpora; Sentence; Corpus linguistics; Text corpus; Metadata; Information retrieval; Machine translation; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008700851,0.0004631366,0.0006930495,0.0002981026,0.0004557836,0.0005507855,0.002697537,0.0001652595,0.0001688265],"category_scores_gemma":[0.0001594506,0.0003380097,0.0004276476,0.0007175936,0.0002773753,0.001717719,0.0002074679,0.0008964901,0.00006122893],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001033407,"about_ca_system_score_gemma":0.0001356864,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007574787,"about_ca_topic_score_gemma":0.00001720761,"domain_scores_codex":[0.9968794,0.000340955,0.0006873396,0.0006078788,0.0006855139,0.0007988913],"domain_scores_gemma":[0.9978443,0.00008381395,0.0005083779,0.0007947543,0.0003476601,0.0004210302],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009917453,0.001621223,0.004340439,0.000288064,0.003829465,0.005155065,0.01816881,0.00007568782,0.02458504,0.238414,0.01382515,0.6887053],"study_design_scores_gemma":[0.002714035,0.001160985,0.005467818,0.0002681618,0.001004223,0.007838163,0.0001178577,0.002505402,0.03319284,0.9287559,0.014978,0.001996618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01279861,0.07866489,0.9055177,0.0004237429,0.0008702454,0.0002830367,0.000006633735,0.0008558636,0.000579252],"genre_scores_gemma":[0.1699201,0.004604169,0.8241637,0.0005539521,0.0001580822,0.00002275169,0.000003414283,0.00005037747,0.0005234753],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6903419,"threshold_uncertainty_score":0.9999072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04397547829965751,"score_gpt":0.265400361353215,"score_spread":0.2214248830535575,"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."}}