{"id":"W2251940628","doi":"10.3115/v1/w14-5706","title":"A Comparative Study of Different Classification Methods for the Identification of Brazilian Portuguese Multiword Expressions","year":2014,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Brazilian Portuguese; Computer science; Identification (biology); Portuguese; Artificial intelligence; Natural language processing; Linguistics","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":[0.008605555,0.001444677,0.0009896377,0.0102187,0.0009484134,0.002325698,0.00107731,0.0008758215,0.002298275],"category_scores_gemma":[0.02773977,0.0003539889,0.0009110534,0.006316313,0.0006127669,0.003332848,0.001246447,0.0009425441,0.002075465],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006533795,"about_ca_system_score_gemma":0.001193501,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002874065,"about_ca_topic_score_gemma":0.004198355,"domain_scores_codex":[0.9914106,0.004258231,0.0009683068,0.001056725,0.002002242,0.0003038514],"domain_scores_gemma":[0.9687182,0.02426919,0.001101979,0.001251251,0.004305319,0.000353958],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009602896,0.0002790436,0.01765539,0.002222701,0.0002908143,0.000241455,0.002460721,0.002551153,0.0208605,0.001840301,0.003643126,0.9469946],"study_design_scores_gemma":[0.0005425768,0.002216555,0.1815931,0.002140212,0.001665842,0.005433056,0.01637852,0.5010725,0.1849498,0.009263527,0.09405794,0.0006863164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4359801,0.01114183,0.5240012,0.001155466,0.0005840414,0.0008995056,0.003166462,0.007761851,0.01530957],"genre_scores_gemma":[0.476592,0.004036389,0.5064479,0.0001740353,0.0001827981,0.0007256131,0.006147883,0.00102408,0.004669385],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0102187,"threshold_uncertainty_score":0.04551107,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06705337433864526,"score_gpt":0.4241045335291538,"score_spread":0.3570511591905086,"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."}}