{"id":"W2951586423","doi":"10.1111/coin.12225","title":"Multi‐representational convolutional neural networks for text classification","year":2019,"lang":"en","type":"article","venue":"Computational Intelligence","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"Nexen (Canada)","funders":"Natural Science Foundation of Tianjin City; National Natural Science Foundation of China","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Natural language processing; Embedding; Focus (optics); Word embedding; Word (group theory); Semantics (computer science); Categorization; Domain (mathematical analysis); Pattern recognition (psychology)","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":[0.0006563306,0.0008930746,0.0004653807,0.001490021,0.000228206,0.000794448,0.0009096417,0.0008251667,0.002368678],"category_scores_gemma":[0.001839739,0.000231499,0.0005983242,0.001569522,0.0002719056,0.001597801,0.0005607789,0.001041569,0.00119329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001069339,"about_ca_system_score_gemma":0.0005523039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008523537,"about_ca_topic_score_gemma":0.008672189,"domain_scores_codex":[0.9996712,0.00007059005,0.00002779186,0.00009898145,0.00007107262,0.00006037519],"domain_scores_gemma":[0.9993744,0.0002715946,0.0001011745,0.00007702853,0.0001480282,0.00002773442],"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":[0.0002777248,0.0002411572,0.002979294,0.0002657677,0.000166051,0.0001509758,0.00008990148,0.2798678,0.01491802,0.007018047,0.01158071,0.6824445],"study_design_scores_gemma":[0.000002783216,0.00001090581,0.00037104,0.000007618457,0.000008256715,0.000008239033,0.000006821987,0.9953411,0.001453309,0.002153729,0.0006327197,0.00000358842],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2298333,0.01023814,0.7350447,0.002796387,0.0006411823,0.0002099584,0.002755184,0.008883164,0.009598008],"genre_scores_gemma":[0.8691782,0.001568286,0.1182476,0.0002609438,0.0002172977,0.00009707623,0.00262055,0.00009995746,0.00771011],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008523537,"threshold_uncertainty_score":0.01694781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0945598607666244,"score_gpt":0.3378425082975396,"score_spread":0.2432826475309152,"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."}}