{"id":"W1571803718","doi":"10.1007/11671299_9","title":"Automatically Determining Allowable Combinations of a Class of Flexible Multiword Expressions","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Measure (data warehouse); Class (philosophy); Collocation (remote sensing); Natural language processing; Simple (philosophy); Artificial intelligence; Noun; Machine learning; Data mining","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":[0.001157923,0.001558588,0.001258792,0.002787333,0.001557162,0.002141994,0.001823065,0.001594743,0.008983289],"category_scores_gemma":[0.006135745,0.001382576,0.001795189,0.002008292,0.0009652807,0.00536059,0.002617142,0.002143,0.002755495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005200122,"about_ca_system_score_gemma":0.001087663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00114721,"about_ca_topic_score_gemma":0.002374111,"domain_scores_codex":[0.9977372,0.000356091,0.0002995705,0.000837445,0.0005324383,0.0002372349],"domain_scores_gemma":[0.9944525,0.003432993,0.0004068903,0.0006256448,0.0008529726,0.0002290282],"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":[0.001565235,0.0004544804,0.01486073,0.001418714,0.0003380178,0.005221341,0.001802247,0.01056598,0.1710296,0.06507118,0.02366299,0.7040095],"study_design_scores_gemma":[0.0002467057,0.0007251834,0.01202715,0.000618289,0.0007536103,0.009747488,0.003977551,0.4159729,0.1936731,0.2690987,0.09273715,0.0004222348],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3155861,0.0009078958,0.6453988,0.0006536074,0.0002547441,0.000480513,0.005097212,0.01461545,0.01700574],"genre_scores_gemma":[0.5194864,0.0003596988,0.4635709,0.0002190418,0.0001138365,0.0003710081,0.007630389,0.003300263,0.004948497],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008983289,"threshold_uncertainty_score":0.03005207,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01519254296208463,"score_gpt":0.273740788390299,"score_spread":0.2585482454282144,"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."}}