{"id":"W1560709708","doi":"10.1007/3-540-45153-6_4","title":"A Statistical Corpus-Based Term Extractor","year":2001,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Perplexity; Extractor; Term (time); Natural language processing; Artificial intelligence; Lexicography; Language model; Linguistics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008306421,0.0006224231,0.0005788159,0.0008780864,0.0002091485,0.000846322,0.004430573,0.0004473864,0.0000660912],"category_scores_gemma":[0.0002130463,0.0005418396,0.0001119872,0.0006267382,0.0008603805,0.0005916611,0.0009790875,0.00120594,0.00004560847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004202867,"about_ca_system_score_gemma":0.0009165219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002086252,"about_ca_topic_score_gemma":0.00003089986,"domain_scores_codex":[0.9956471,0.00004753216,0.0005323462,0.001736792,0.001241416,0.0007948082],"domain_scores_gemma":[0.9966975,0.0009155124,0.0003032244,0.001561568,0.0002759637,0.000246189],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000113062,0.00004099789,0.00007916209,0.00007236388,0.000005167734,0.0007352338,0.0000862191,0.0004171735,0.0005683193,0.07505599,0.00004497599,0.9228831],"study_design_scores_gemma":[0.0004126255,0.0003537508,0.0001928113,0.001140966,0.00001346601,0.0002666994,2.289695e-8,0.2114555,0.007047263,0.7743796,0.003307399,0.001429944],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001663911,0.001708906,0.9942954,0.0004177252,0.0008881701,0.0003706288,0.00001357498,0.0007162335,0.001572761],"genre_scores_gemma":[0.05156066,0.00002523828,0.9463241,0.001552743,0.0002878761,0.00001157957,0.00001240204,0.00004397566,0.0001814794],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9214532,"threshold_uncertainty_score":0.9997033,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01606606083387984,"score_gpt":0.2780418839368485,"score_spread":0.2619758231029687,"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."}}