{"id":"W2926337278","doi":"10.48550/arxiv.1904.00132","title":"ANA at SemEval-2019 Task 3: Contextual Emotion detection in Conversations through hierarchical LSTMs and BERT","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"SemEval; Computer science; Task (project management); Utterance; Context (archaeology); Artificial intelligence; Emotion detection; Natural language processing; Emotion 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":[0.0002686476,0.0002424696,0.0003391684,0.0003503208,0.0001626924,0.0001177608,0.0005301259,0.0002629512,0.00004204663],"category_scores_gemma":[0.00002568018,0.0002796808,0.0001619612,0.0005418448,0.0001023951,0.0005349803,0.001245072,0.0004301905,0.0001009849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000301404,"about_ca_system_score_gemma":0.00007762252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004605587,"about_ca_topic_score_gemma":0.0003137591,"domain_scores_codex":[0.9981205,0.0002093064,0.0002518475,0.001021165,0.0001286782,0.0002685142],"domain_scores_gemma":[0.9987972,0.0001486312,0.0002355992,0.0006445741,0.00008548345,0.00008846362],"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":[0.0004390127,0.0007833611,0.2635868,0.0003757497,0.001338601,0.000400775,0.01885192,0.3994571,0.003159588,0.2925701,0.002724141,0.01631292],"study_design_scores_gemma":[0.001141352,0.0000778254,0.02489821,0.00009200449,0.00007989934,0.000005294193,0.0002869974,0.9659731,0.0002971466,0.005849904,0.0008566146,0.0004415928],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6407655,0.00006772987,0.3575023,0.0001605163,0.0004694781,0.00022253,0.000007455782,0.00006292512,0.0007415809],"genre_scores_gemma":[0.9973935,0.0002847822,0.0004915246,0.00009962484,0.00004977785,6.788968e-7,0.000051185,0.0000104421,0.0016185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.566516,"threshold_uncertainty_score":0.9999655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0532106818535751,"score_gpt":0.203018902642434,"score_spread":0.1498082207888589,"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."}}