{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008422114,0.0001586572,0.0002275862,0.0001483403,0.0001389238,0.0001006347,0.0007688972,0.0001038331,0.00002098449],"category_scores_gemma":[0.005511887,0.0001244428,0.0000425809,0.0004154443,0.0001195002,0.0001825014,0.0003437623,0.0002445078,0.000002077954],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004636355,"about_ca_system_score_gemma":0.0000746346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002708059,"about_ca_topic_score_gemma":0.00002531538,"domain_scores_codex":[0.9983386,0.00005787001,0.000440098,0.0003536309,0.0004375628,0.0003722024],"domain_scores_gemma":[0.9981493,0.0007238176,0.0001523179,0.0004038384,0.0004292215,0.0001414858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004915603,0.0002331196,0.00532179,0.0001078533,0.00003365548,0.0002183432,0.001059529,0.00002996848,0.3436032,0.5885035,0.0002632197,0.0605766],"study_design_scores_gemma":[0.0004765572,0.0001266269,0.003592775,0.0006418315,0.00003682477,0.000056509,0.0001087459,0.07470611,0.8309149,0.08789583,0.0006606816,0.0007826412],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009768275,0.0002906127,0.9873223,0.0000337578,0.0001681363,0.00009952173,0.000003967082,0.0005956293,0.001717795],"genre_scores_gemma":[0.4938127,7.46338e-7,0.5060879,0.000034465,0.00003402969,5.370931e-7,0.000001455097,0.000007243289,0.00002095212],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5006077,"threshold_uncertainty_score":0.6598642,"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."}}