{"id":"W2123215530","doi":"10.1162/coli.08-010-r1-07-048","title":"Unsupervised Type and Token Identification of Idiomatic Expressions","year":2009,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Atomic Energy of Canada Limited; University of Toronto","keywords":"Linguistics; Identification (biology); Interpretation (philosophy); Computer science; Natural language processing; Literal (mathematical logic); Task (project management); Context (archaeology); Security token; Artificial intelligence; Semantic property; Expression (computer science); Psychology; History","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001308024,0.00006790786,0.0000956415,0.00008631039,0.00006676902,0.00006101749,0.0002943111,0.00003605475,0.000001246592],"category_scores_gemma":[0.00137965,0.00006378917,0.00001392329,0.0002907392,0.00002588565,0.00006021193,0.00006178629,0.00005905602,0.00000275502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001177222,"about_ca_system_score_gemma":0.00005857098,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001357859,"about_ca_topic_score_gemma":6.684039e-8,"domain_scores_codex":[0.9993083,0.0000233598,0.000249956,0.0001517497,0.000189736,0.00007682151],"domain_scores_gemma":[0.9988797,0.0001075694,0.0001202622,0.0001696792,0.0006842895,0.00003847907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006065298,0.00008136348,0.0001398941,0.00006088792,0.000008423167,0.00000693512,0.000667673,0.001302814,0.01013905,0.9691526,0.0005407694,0.01789354],"study_design_scores_gemma":[0.000119594,0.00006118437,0.003332626,0.00007009749,0.000008154714,0.000006895634,0.000008525846,0.2276384,0.006827014,0.7616497,0.0001604881,0.000117324],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007569154,0.001098612,0.9902043,0.0002482025,0.0002105895,0.00009606723,0.000004030861,0.0002055377,0.0003634446],"genre_scores_gemma":[0.6096856,0.000003748404,0.3901688,0.00007969642,0.0000393273,6.443012e-7,0.000008813236,0.000002045011,0.00001132167],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6021165,"threshold_uncertainty_score":0.2601247,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01564023181424613,"score_gpt":0.2969218139515016,"score_spread":0.2812815821372555,"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."}}