{"id":"W2001214180","doi":"10.5539/cis.v3n1p168","title":"Automatic Recognition of Focus and Interrogative Word in Chinese Question for Classification","year":2010,"lang":"en","type":"article","venue":"Computer and Information Science","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Interrogative; Computer science; Focus (optics); Artificial intelligence; Natural language processing; Interrogative word; CRFS; Conditional random field; Word (group theory); Parsing; Part of speech; Text segmentation; Segmentation; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007417959,0.00005502884,0.00007698126,0.0002927266,0.00006922272,0.0001503245,0.0002139876,0.00002805373,8.917901e-7],"category_scores_gemma":[0.0001191814,0.00004681146,0.000009552136,0.0003776161,0.0001183913,0.005910766,0.000102477,0.00006567515,0.000001441311],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001331403,"about_ca_system_score_gemma":0.00004380711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009515821,"about_ca_topic_score_gemma":0.000009695817,"domain_scores_codex":[0.9993691,0.00001218984,0.0002653728,0.0001298624,0.0001324595,0.00009102447],"domain_scores_gemma":[0.9994349,0.00007059366,0.0001307493,0.0001427149,0.0001818297,0.0000391783],"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":[0.000001646789,0.00000646488,0.001026966,0.00002410957,4.682884e-7,2.326628e-8,0.002930626,0.00001569434,0.0008714257,0.01429019,0.000002616156,0.9808298],"study_design_scores_gemma":[0.0002095117,0.0000324163,0.1032989,0.00002828817,5.691629e-7,0.00000511669,0.00003740724,0.8883827,0.0005204249,0.007413641,0.00002069236,0.00005023545],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4783875,0.000002537683,0.5210822,0.000145746,0.0001471906,0.0001160419,6.927527e-7,0.00001784554,0.0001002899],"genre_scores_gemma":[0.8272175,0.000004398319,0.1726883,0.00006055549,0.0000139755,0.00001230128,0.000001752343,6.86765e-7,4.765345e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9807795,"threshold_uncertainty_score":0.4285163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02397677736884165,"score_gpt":0.2882214725990372,"score_spread":0.2642446952301956,"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."}}