{"id":"W2166456646","doi":"10.3115/1613704.1613706","title":"Distinguishing subtypes of multiword expressions using linguistically-motivated statistical measures","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Lexicon; Idiosyncrasy; Natural language processing; Artificial intelligence; Property (philosophy); Encoding (memory); Semantics (computer science)","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":[0.004271748,0.0005707252,0.0009219145,0.004641969,0.001540457,0.004397244,0.001385995,0.001173454,0.002112899],"category_scores_gemma":[0.02836606,0.000411895,0.0007679493,0.003030529,0.002097036,0.006026143,0.001940947,0.001491594,0.0007508171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001102351,"about_ca_system_score_gemma":0.001096278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00108643,"about_ca_topic_score_gemma":0.001560764,"domain_scores_codex":[0.9954314,0.001061188,0.0008612928,0.001176317,0.001249303,0.0002205691],"domain_scores_gemma":[0.9667213,0.01652232,0.006523252,0.004256006,0.004785826,0.001191293],"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":[0.001228103,0.0004727601,0.1862635,0.0008449653,0.000248699,0.001212915,0.00628765,0.01116146,0.1248276,0.2577542,0.004155061,0.405543],"study_design_scores_gemma":[0.0001047141,0.0004795476,0.114536,0.0002291984,0.0002553128,0.003036696,0.005597788,0.3152317,0.05564442,0.4888057,0.01571452,0.0003642433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6050488,0.0004825896,0.3807609,0.0008996966,0.0001136733,0.000373236,0.0008788094,0.0009733018,0.01046902],"genre_scores_gemma":[0.8585174,0.0001398733,0.138355,0.0001821472,0.0001185232,0.0003098796,0.001099795,0.0002926005,0.0009847727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.004641969,"threshold_uncertainty_score":0.02259141,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03124131390052613,"score_gpt":0.3303614893980023,"score_spread":0.2991201754974762,"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."}}