{"id":"W3123538310","doi":"10.18653/v1/2021.eacl-main.135","title":"SpanEmo: Casting Multi-label Emotion Classification as Span-prediction","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Open Text (Canada)","funders":"Umm Al-Qura University","keywords":"Sentence; Computer science; Natural language processing; Artificial intelligence; Sentiment analysis; Function (biology); Profiling (computer programming); Machine learning; Speech recognition","routes":{"ca_aff":true,"ca_fund":false,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005034634,0.0002828534,0.000329157,0.0002920557,0.000212136,0.0009667758,0.0007185558,0.0002951056,0.0001932713],"category_scores_gemma":[0.0001090111,0.0002890321,0.000194857,0.0004556771,0.00002231263,0.0004574915,0.001106046,0.0004617753,0.0001525107],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001470346,"about_ca_system_score_gemma":0.0001716222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002335615,"about_ca_topic_score_gemma":0.00003012969,"domain_scores_codex":[0.9973575,0.0001476289,0.0005865187,0.001084674,0.0005431974,0.0002804566],"domain_scores_gemma":[0.9980913,0.00005777143,0.0004288724,0.001001332,0.000308877,0.0001117886],"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":[0.00001504445,0.001744061,0.0290644,0.0004825767,0.001111015,0.0001371555,0.009258416,0.01382514,0.03974627,0.03093596,0.005499748,0.8681802],"study_design_scores_gemma":[0.0002728016,0.00001906436,0.01366657,0.0001599497,0.00004641743,0.00001284125,0.0005717226,0.9836077,0.00109354,0.0001275149,0.0001602757,0.0002615956],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06468546,0.0001515829,0.9279017,0.0007934368,0.002341886,0.0001870299,0.000002641853,0.000373733,0.003562504],"genre_scores_gemma":[0.6232615,0.0001713014,0.3720093,0.0002293755,0.0004264055,0.00002918329,0.0004680684,0.00002432949,0.003380577],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9697826,"threshold_uncertainty_score":0.9999562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1207520480778474,"score_gpt":0.3291691309771665,"score_spread":0.2084170828993192,"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."}}