{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002379122,0.0001063418,0.0001131026,0.0001446382,0.0003163224,0.0001441811,0.0004526318,0.00006017979,0.000003160062],"category_scores_gemma":[0.00006208334,0.00007834993,0.00004603686,0.0002386226,0.00004921762,0.002744498,0.00005491797,0.00004306384,0.000004640705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000389509,"about_ca_system_score_gemma":0.00004996909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004107605,"about_ca_topic_score_gemma":0.000001294017,"domain_scores_codex":[0.9992111,0.00001615326,0.0002590901,0.0001984993,0.0001151538,0.0001999895],"domain_scores_gemma":[0.9990696,0.0001577178,0.0001793074,0.0003668106,0.0001982948,0.00002821674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001089391,0.000006196607,0.00007371762,0.00002297918,0.00001039985,2.488724e-8,0.0004090248,0.0002371388,0.0007007345,0.7362561,0.0005912669,0.2616816],"study_design_scores_gemma":[0.0004783485,0.00008705971,0.0009631625,0.000004870018,0.0000061266,0.000007894764,0.0001991989,0.9308286,0.008926954,0.05371745,0.004636806,0.0001435836],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003296047,0.0000177834,0.9925744,0.001591297,0.00008824228,0.0007226713,0.00000179114,0.0005895271,0.001118276],"genre_scores_gemma":[0.4103941,0.000003815609,0.5890509,0.00008198419,0.000007901355,0.0001943526,0.00001306019,0.000003282398,0.0002505624],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9305914,"threshold_uncertainty_score":0.3195018,"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."}}