{"id":"W3034480528","doi":"10.18653/v1/2020.acl-main.514","title":"A Comprehensive Analysis of Preprocessing for Word Representation Learning in Affective Tasks","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Preprocessor; Computer science; Sentiment analysis; Artificial intelligence; Natural language processing; Task (project management); Word (group theory); Data pre-processing; Representation (politics); Task analysis; Support vector machine; Identification (biology); Machine learning; Linguistics; Engineering","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":[0.00009364016,0.00005348299,0.0001931705,0.0001554199,0.00002826678,0.00003352043,0.0001904692,0.000023916,0.000004503679],"category_scores_gemma":[0.0001546312,0.00005268293,0.00007058293,0.001223438,0.000009959465,0.0002349215,0.00009721975,0.00006614286,6.479168e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000163706,"about_ca_system_score_gemma":0.00002384612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009534442,"about_ca_topic_score_gemma":0.00002533485,"domain_scores_codex":[0.999221,0.00005303705,0.0001864536,0.000331912,0.0001101745,0.00009748294],"domain_scores_gemma":[0.9994003,0.0002255932,0.00009653382,0.0001482893,0.000100036,0.00002927303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002239824,0.00001938104,0.02516806,0.00005683266,0.0001455567,0.000001675328,0.01257062,0.858057,0.004517314,0.002016803,0.00001147826,0.09741289],"study_design_scores_gemma":[0.0001988451,0.00002690551,0.01092021,0.000008311205,0.00003140032,1.246722e-7,0.0004954654,0.9855174,0.002377903,0.0003412462,0.00002904741,0.00005317318],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.236425,0.0000257143,0.7626692,0.0003974375,0.00001303045,0.0001245063,2.397349e-7,0.00004736474,0.0002974897],"genre_scores_gemma":[0.9322008,0.000001153992,0.0675979,0.0001475279,0.00001132976,0.0000133392,0.000002185101,0.000002562273,0.00002317472],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6957758,"threshold_uncertainty_score":0.2148348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06387737328250263,"score_gpt":0.3308107333637708,"score_spread":0.2669333600812681,"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."}}