{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009244239,0.0008892823,0.0003767034,0.0003632658,0.0002031386,0.0008259786,0.0006163039,0.0006734193,0.002598281],"category_scores_gemma":[0.003258656,0.0002243073,0.0004559544,0.0003324103,0.0004058784,0.001926185,0.0008020859,0.001246828,0.0009217695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004156661,"about_ca_system_score_gemma":0.0004222447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001588026,"about_ca_topic_score_gemma":0.003114126,"domain_scores_codex":[0.9997092,0.00009990723,0.00001449702,0.0000885547,0.00005547634,0.00003228348],"domain_scores_gemma":[0.9988211,0.0007229668,0.00008949231,0.0001469033,0.0001722706,0.00004723093],"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":[0.0004425138,0.0003011116,0.009186788,0.0003421918,0.0002250411,0.0002036638,0.0003932471,0.1208091,0.06901467,0.01234455,0.006766578,0.7799705],"study_design_scores_gemma":[0.00001599353,0.0001623935,0.003297467,0.00003796332,0.00007475411,0.00008664264,0.00004488445,0.9564756,0.01612429,0.02034621,0.003317388,0.00001638131],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1998343,0.002291032,0.7836497,0.001850345,0.0002440817,0.0001025068,0.0003153037,0.002971037,0.008741785],"genre_scores_gemma":[0.9361156,0.000808796,0.0576042,0.0002630405,0.0001502412,0.00005224069,0.0004242317,0.0001426959,0.004438915],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002598281,"threshold_uncertainty_score":0.008692145,"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."}}