{"id":"W2171694517","doi":"10.3115/1219044.1219071","title":"Automatic clustering of collocation for detecting practical sense boundary","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Collocation (remote sensing); Computer science; Boundary (topology); Bottleneck; Cluster analysis; Natural language processing; Sense (electronics); Confusion; Resource (disambiguation); Word-sense disambiguation; Artificial intelligence; Information retrieval; Machine learning; Mathematics; WordNet; Engineering","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":[0.001812256,0.001271046,0.001014689,0.007941107,0.002588264,0.001714412,0.001415739,0.001532432,0.004054284],"category_scores_gemma":[0.01100694,0.0006746002,0.0009188906,0.005055693,0.001190227,0.003239264,0.00231431,0.001238029,0.003444033],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008243953,"about_ca_system_score_gemma":0.001689856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004400651,"about_ca_topic_score_gemma":0.005766446,"domain_scores_codex":[0.9955204,0.001315587,0.0003796631,0.001584099,0.0009565177,0.0002438372],"domain_scores_gemma":[0.9936813,0.002138239,0.0005306528,0.001238734,0.002167335,0.0002436922],"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":[0.0006807579,0.0002232346,0.01213791,0.001356068,0.0002556584,0.0009170616,0.003898294,0.01256039,0.1559273,0.02253551,0.02856925,0.7609386],"study_design_scores_gemma":[0.0001925382,0.0003899093,0.03374667,0.0004052687,0.0003323733,0.003482064,0.005954602,0.649538,0.1407594,0.06324829,0.1014782,0.0004727258],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.067405,0.001081388,0.9209667,0.000294666,0.0002671078,0.0003430497,0.0009171841,0.003960114,0.004764732],"genre_scores_gemma":[0.2617576,0.0003058595,0.7308832,0.0001032664,0.00006118823,0.0002621875,0.003582811,0.000550587,0.002493437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007941107,"threshold_uncertainty_score":0.01356292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02097973501162764,"score_gpt":0.3230780631393331,"score_spread":0.3020983281277055,"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."}}