{"id":"W2536295050","doi":"10.1109/fskd.2016.7603424","title":"Chinese term extraction from web pages based on expected point-wise mutual information","year":2016,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Term (time); Lexicon; Point (geometry); Computer science; Information retrieval; Word (group theory); Mutual information; Information extraction; Artificial intelligence; Natural language processing; Precision and recall; Data mining; Mathematics","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":[0.0001135688,0.0001656626,0.0001478877,0.0002900863,0.00007034841,0.0001185575,0.0004663804,0.00007160271,0.0002260687],"category_scores_gemma":[0.0001516567,0.00009877518,0.00008261931,0.0003559258,0.00002626454,0.003749962,0.00008186499,0.00007770789,0.0003180822],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009542538,"about_ca_system_score_gemma":0.00003371105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001717458,"about_ca_topic_score_gemma":0.00003252285,"domain_scores_codex":[0.9989017,0.00005042791,0.0002870214,0.0002585916,0.0003257611,0.000176514],"domain_scores_gemma":[0.9987248,0.0002461082,0.0001639457,0.000696848,0.00009650767,0.00007175076],"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":[0.00008648251,0.0002489036,0.009641188,0.000006672348,0.00003993915,0.00001407358,0.0004921716,0.00008236211,0.2089112,0.005164928,0.008231066,0.767081],"study_design_scores_gemma":[0.003721256,0.0005923754,0.1605993,0.0002078986,0.00003650936,0.000008873915,0.00008590762,0.4629696,0.3340858,0.02558691,0.01053396,0.001571654],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05960152,0.000004281868,0.9331543,0.001287201,0.00009555187,0.0001219138,0.00000546574,0.001124861,0.004604946],"genre_scores_gemma":[0.9059979,0.00001168555,0.09320685,0.000489858,0.00005136251,0.00002758579,0.00001617144,0.00000617157,0.0001923563],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8463964,"threshold_uncertainty_score":0.4088409,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006995051740656491,"score_gpt":0.2656118688887918,"score_spread":0.2586168171481353,"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."}}