{"id":"W1482760454","doi":"10.5555/1793274.1793346","title":"Methods for augmenting semantic models with structural information for text classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; ENCODE; Artificial intelligence; Semantics (computer science); Representation (politics); Feature (linguistics); Word (group theory); Syntactic structure; Information retrieval; Syntax; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004311717,0.0009587228,0.0008843809,0.002902557,0.0006054899,0.001580246,0.001580488,0.001241913,0.002528616],"category_scores_gemma":[0.01541842,0.0004268456,0.001374561,0.002366543,0.001014772,0.005721844,0.001489168,0.001952444,0.001434569],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001088065,"about_ca_system_score_gemma":0.001279356,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001677789,"about_ca_topic_score_gemma":0.00384949,"domain_scores_codex":[0.9977023,0.001073074,0.0001353054,0.0003048476,0.0006918758,0.00009257565],"domain_scores_gemma":[0.9880459,0.008010183,0.0006952357,0.00161108,0.001471481,0.0001661305],"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":[0.0005912813,0.0007058959,0.005481428,0.0003661035,0.0002483495,0.00008610931,0.0002950877,0.1300294,0.01150147,0.03986325,0.008522087,0.8023096],"study_design_scores_gemma":[0.00003989263,0.00007291631,0.0004976927,0.00003309367,0.0000552243,0.00003655771,0.00004747135,0.9566041,0.003867954,0.03642488,0.002295681,0.00002444991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03781088,0.0005726195,0.9555326,0.001035665,0.0001226488,0.0001751453,0.0003459267,0.002278732,0.002125789],"genre_scores_gemma":[0.2979673,0.0003169853,0.6974695,0.000212112,0.0001809053,0.0004505652,0.001345017,0.0002057309,0.001851898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004311717,"threshold_uncertainty_score":0.02280277,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07300728272857057,"score_gpt":0.3366887500066414,"score_spread":0.2636814672780708,"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."}}