{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004508077,0.00006169137,0.0000977009,0.00006840276,0.00003772731,0.00003869778,0.0003238479,0.00005424222,0.00007350524],"category_scores_gemma":[0.0000238643,0.00005633792,0.00004143008,0.0003014391,0.00001632077,0.0002817353,0.00008937746,0.00006771684,0.0001733295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002827146,"about_ca_system_score_gemma":0.00004617385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009691757,"about_ca_topic_score_gemma":8.124451e-7,"domain_scores_codex":[0.9992411,0.00004173796,0.0001868769,0.0002589502,0.0001344886,0.0001369204],"domain_scores_gemma":[0.9993036,0.00004404722,0.000107964,0.0004167106,0.00008856659,0.00003913299],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003691138,0.00001926121,0.01726967,0.00001974842,0.000005329722,3.154721e-7,0.0002735789,0.00004680757,0.8242321,0.1505971,0.0001196004,0.007412764],"study_design_scores_gemma":[0.0002570279,0.00003056228,0.03606266,0.0000377517,0.000004726865,0.000009027522,0.00007094417,0.278141,0.6806902,0.002867469,0.001626332,0.0002023126],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6233412,0.0000262032,0.3745527,0.0001970031,0.000194551,0.00007263947,4.956112e-7,0.0000531428,0.001562018],"genre_scores_gemma":[0.9553159,0.000002042676,0.04407084,0.0001052533,0.00001471468,6.975812e-7,0.000001926414,0.00000351351,0.0004851332],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3319747,"threshold_uncertainty_score":0.2297394,"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."}}