{"id":"W2914713622","doi":"10.18653/v1/w18-5429","title":"Importance of Self-Attention for Sentiment Analysis","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada; Nvidia","keywords":"Interpretability; Computer science; Sentiment analysis; Task (project management); Artificial intelligence; Word (group theory); Baseline (sea); Machine learning; Natural language processing; Architecture; Order (exchange); Task analysis; 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":[0.0001709876,0.00003578274,0.00008182236,0.0000717152,0.00002754283,0.00001651151,0.0002195308,0.00001294885,0.00002284871],"category_scores_gemma":[0.000004260673,0.00003082659,0.00008131889,0.0002820966,0.000007671711,0.000111096,0.00005454642,0.00000971057,0.000006063852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001270646,"about_ca_system_score_gemma":0.0000114623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001223081,"about_ca_topic_score_gemma":0.00002800788,"domain_scores_codex":[0.999476,0.000006823253,0.0001528243,0.0001749074,0.0001019661,0.00008753359],"domain_scores_gemma":[0.9994671,0.00001278364,0.00006420398,0.0003352169,0.0001002821,0.00002037474],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001089312,0.0003928425,0.3955171,0.00008690181,0.001790458,0.00000175837,0.001777846,0.0008215812,0.0133515,0.5417704,0.003143754,0.04133495],"study_design_scores_gemma":[0.0001189623,0.00003862265,0.01476699,0.000001744777,0.00006716446,3.04838e-7,0.000008542908,0.9763848,0.006368505,0.001832851,0.0003553483,0.00005613177],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1789536,0.000005333562,0.8197221,0.0001932915,0.00007284764,0.00006468264,3.417338e-7,0.00004966472,0.0009382482],"genre_scores_gemma":[0.6688337,3.748772e-7,0.3307262,0.00006371574,0.00002709526,0.0000039601,4.961343e-7,0.000001012877,0.0003434937],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9755632,"threshold_uncertainty_score":0.1257072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01739562852435575,"score_gpt":0.2703236454028812,"score_spread":0.2529280168785254,"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."}}