{"id":"W2469995694","doi":"10.18653/v1/s16-1060","title":"UWaterloo at SemEval-2016 Task 5: Minimally Supervised Approaches to Aspect-Based Sentiment Analysis","year":2016,"lang":"en","type":"article","venue":"","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"SemEval; Computer science; Sentiment analysis; Task (project management); Artificial intelligence; Natural language processing; Machine learning; Engineering","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005972549,0.0003087563,0.0004732895,0.0007423028,0.0001896581,0.0002705819,0.00109622,0.00007250391,0.00162286],"category_scores_gemma":[0.00001896913,0.000188418,0.0005438098,0.001668755,0.000040684,0.0003558789,0.0005360114,0.00004242789,0.001429494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001757603,"about_ca_system_score_gemma":0.0000662659,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005313376,"about_ca_topic_score_gemma":0.0001073888,"domain_scores_codex":[0.9969791,0.000138512,0.0005320905,0.001052653,0.0007163261,0.0005813643],"domain_scores_gemma":[0.9981101,0.0001516752,0.0001264928,0.001186947,0.000086202,0.0003385954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003834775,0.002423661,0.3237522,0.00008730271,0.01366071,0.0001525935,0.006110386,0.005803662,0.3187318,0.031026,0.1072928,0.1905754],"study_design_scores_gemma":[0.004570419,0.0006448497,0.03852529,0.0001313477,0.001658787,0.00000523759,0.0002560521,0.5277402,0.3892151,0.0003242467,0.03435181,0.002576674],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2478638,0.00007240899,0.7334939,0.01278916,0.000203417,0.0003076549,0.000009988339,0.0003079012,0.00495179],"genre_scores_gemma":[0.9090113,0.000004426287,0.06582141,0.001043912,0.00008824431,0.00004222275,0.00001737758,0.00001899256,0.02395212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6676725,"threshold_uncertainty_score":0.999348,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06110085178336443,"score_gpt":0.2392317469160083,"score_spread":0.1781308951326439,"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."}}