{"id":"W1565752952","doi":"10.1007/3-540-45486-1_11","title":"Collocation Discovery for Optimal Bilingual Lexicon Development","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Lexicon; Collocation (remote sensing); Natural language processing; Artificial intelligence; Variety (cybernetics); Lexicography; Machine translation; Linguistics; Machine learning","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":[0.001626819,0.001355202,0.001900362,0.004508838,0.001704255,0.002714248,0.002017754,0.001388112,0.03151518],"category_scores_gemma":[0.008414167,0.001354197,0.001433555,0.003991289,0.0008208401,0.005445015,0.004176963,0.001625698,0.01475789],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000879011,"about_ca_system_score_gemma":0.003815677,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004395818,"about_ca_topic_score_gemma":0.01023169,"domain_scores_codex":[0.9980747,0.0006232994,0.0002468289,0.0004898764,0.0003326109,0.0002326198],"domain_scores_gemma":[0.9960387,0.001849092,0.0001314955,0.0005942495,0.001253562,0.000132997],"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":[0.0004778946,0.0001376081,0.000995499,0.0006232984,0.00008586523,0.0004958764,0.0003763594,0.008845214,0.02006585,0.02296609,0.03213138,0.9127991],"study_design_scores_gemma":[0.0004029474,0.0002661047,0.001408165,0.0002155613,0.0003310388,0.001623701,0.001633942,0.723914,0.06576204,0.1475496,0.05673042,0.0001624866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02142134,0.0007104059,0.9523187,0.0004650359,0.0002316812,0.0002876151,0.001838774,0.01392123,0.00880524],"genre_scores_gemma":[0.1682714,0.0005220936,0.8129278,0.000192412,0.0001399116,0.0003779857,0.008730462,0.0023361,0.006501748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03151518,"threshold_uncertainty_score":0.1054288,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01549751402483348,"score_gpt":0.2701919790296989,"score_spread":0.2546944650048655,"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."}}