{"id":"W2991402558","doi":"10.26615/978-954-452-056-4_062","title":"Classification of Micro-Texts Using Sub-Word Embeddings","year":2019,"lang":"en","type":"article","venue":"","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"National Institute for Materials Science; Natural Sciences and Engineering Research Council of Canada; Dalhousie University","keywords":"Computer science; Word (group theory); Natural language processing; Artificial intelligence; Character (mathematics); Vocabulary; Word embedding; Feature (linguistics); Perceptron; Feature extraction; Layer (electronics); n-gram; Speech recognition; Embedding; Language model; Artificial neural network; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000508574,0.0009087516,0.0004774742,0.003126985,0.0002691477,0.001133884,0.0004002545,0.0006348535,0.002946565],"category_scores_gemma":[0.002882694,0.0001641322,0.0004716961,0.001955659,0.0002010594,0.002485878,0.0007849258,0.0006199116,0.004231678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002324839,"about_ca_system_score_gemma":0.000258561,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004667845,"about_ca_topic_score_gemma":0.0009296024,"domain_scores_codex":[0.9994209,0.000092792,0.00009945175,0.0001852054,0.0001326011,0.00006908558],"domain_scores_gemma":[0.9980158,0.0006845834,0.0003558712,0.0002697074,0.0005345521,0.0001395335],"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":[0.0005727557,0.0004130825,0.02468671,0.0002874846,0.0001034787,0.0003235095,0.0004396637,0.004906513,0.06356489,0.001525478,0.008546142,0.8946302],"study_design_scores_gemma":[0.00004592966,0.0005447571,0.04529386,0.0001119188,0.0001056183,0.0007889014,0.001299365,0.844838,0.07294063,0.01287091,0.02107302,0.00008700903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5129063,0.001338683,0.4596788,0.0008315842,0.0008500979,0.0004966075,0.005922783,0.01006037,0.007914773],"genre_scores_gemma":[0.7952715,0.0005496455,0.185352,0.00009496862,0.0002557517,0.0002188804,0.007297313,0.000230896,0.01072899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003126985,"threshold_uncertainty_score":0.009857237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04542662089416143,"score_gpt":0.302340903005371,"score_spread":0.2569142821112095,"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."}}