{"id":"W2779949567","doi":"10.26615/978-2-9701095-2-5_001","title":"A Comparison of Three Metrics for Detecting Cross- Linguistic Variations in Information Volume and Multiword Expressions Between Parallel Bitexts","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Metric (unit); Computer science; Annotation; Python (programming language); Artificial intelligence; Natural language processing; Word (group theory); Variation (astronomy); Volume (thermodynamics); Character (mathematics); Pattern recognition (psychology); Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.01066071,0.00177253,0.001261043,0.01609405,0.0009036961,0.004099649,0.001552142,0.001426401,0.001449716],"category_scores_gemma":[0.05719033,0.0005022831,0.0008899003,0.009430002,0.00131087,0.004432951,0.002786707,0.0010487,0.0006821023],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001570318,"about_ca_system_score_gemma":0.001063634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004354013,"about_ca_topic_score_gemma":0.004727411,"domain_scores_codex":[0.9860701,0.00428486,0.001612156,0.002197604,0.005223785,0.0006114639],"domain_scores_gemma":[0.937999,0.03827114,0.004853364,0.004963975,0.01282515,0.001087494],"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":[0.003517202,0.0005370529,0.09870712,0.002324732,0.001739639,0.000440877,0.004083246,0.0259882,0.06701791,0.007945484,0.008323882,0.7793745],"study_design_scores_gemma":[0.0003695417,0.003562645,0.3615327,0.0004004652,0.0007391729,0.002283931,0.004169935,0.4003562,0.1904104,0.01444343,0.02088048,0.000851094],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6836404,0.004652094,0.2869287,0.0004036824,0.0003213243,0.0004995353,0.004610754,0.0095624,0.009381011],"genre_scores_gemma":[0.6945233,0.0006933121,0.2942733,0.00007199321,0.0001045432,0.0005525597,0.006828543,0.001094706,0.001857631],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01609405,"threshold_uncertainty_score":0.05637991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0570523413147736,"score_gpt":0.3881733983324355,"score_spread":0.3311210570176619,"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."}}