{"id":"W1806134291","doi":"10.5555/1793274.1793337","title":"Integrating structure and meaning: a new method for encoding structure for text classification","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; ENCODE; Natural language processing; Encoding (memory); Artificial intelligence; Representation (politics); Word (group theory); Semantics (computer science); Feature (linguistics); Syntactic structure; Curse of dimensionality; Computation; Scheme (mathematics); Information retrieval; Linguistics; Syntax; Algorithm; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020994,0.001002287,0.001035657,0.00510304,0.001159174,0.003026098,0.00148373,0.001283916,0.00435584],"category_scores_gemma":[0.01139758,0.0006334471,0.001550844,0.005353804,0.001450931,0.009154588,0.002606229,0.002255299,0.002464132],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009436507,"about_ca_system_score_gemma":0.001894986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001951573,"about_ca_topic_score_gemma":0.002817665,"domain_scores_codex":[0.997693,0.0004830819,0.0004137874,0.0004882167,0.0008079825,0.0001138769],"domain_scores_gemma":[0.9945328,0.002265577,0.0004493468,0.001315424,0.001242475,0.0001943412],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002619856,0.0001066954,0.001547505,0.000524339,0.0001028716,0.0001545094,0.001352579,0.002775594,0.02174268,0.08429202,0.02055187,0.8665873],"study_design_scores_gemma":[0.0001606754,0.000481487,0.002992215,0.0006462134,0.000536282,0.001066032,0.001060744,0.2780399,0.05206482,0.4854498,0.1772242,0.0002776767],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005606349,0.0005233394,0.9856337,0.0005506318,0.0003164476,0.000183091,0.001178939,0.004210743,0.001796697],"genre_scores_gemma":[0.04414169,0.0004820108,0.949353,0.0002672434,0.0002430948,0.0004045177,0.001816334,0.0006478406,0.002644334],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00510304,"threshold_uncertainty_score":0.01457179,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05483125928167303,"score_gpt":0.3224206707254743,"score_spread":0.2675894114438012,"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."}}