{"id":"W6910351232","doi":"10.48448/0bd4-tp11","title":"Better Handling Coreference Resolution in Aspect Level Sentiment Classification by Fine-Tuning Language Models | VIDEO","year":2023,"lang":"en","type":"other","venue":"Open MIND","topic":"AI in Service Interactions","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Coreference; Resolution (logic); Language model; Language understanding; Pattern recognition (psychology); Natural language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008855513,0.0008027725,0.0005897988,0.0006943372,0.000506085,0.001336115,0.001019776,0.0009811396,0.005307652],"category_scores_gemma":[0.003654243,0.000278742,0.0006105091,0.0006100883,0.0002596276,0.002154238,0.001191222,0.0018878,0.003775482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004245556,"about_ca_system_score_gemma":0.0005771134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005401284,"about_ca_topic_score_gemma":0.009052012,"domain_scores_codex":[0.9992747,0.0001742844,0.00004431007,0.0002406274,0.000150384,0.0001157983],"domain_scores_gemma":[0.9991053,0.0002709221,0.00005877638,0.0001934787,0.0003328788,0.00003867117],"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":[0.0005091309,0.0002495945,0.003912179,0.0001958354,0.0001254615,0.0002270796,0.0002066665,0.01457389,0.08773632,0.004032463,0.05690276,0.8313286],"study_design_scores_gemma":[0.00003781368,0.00008485414,0.002101251,0.00002618003,0.00004417567,0.0001217692,0.0001391595,0.9378526,0.03717543,0.00749272,0.01489542,0.00002854201],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1244342,0.001248295,0.8325692,0.001462956,0.001087916,0.0002064925,0.00240971,0.02290571,0.01367554],"genre_scores_gemma":[0.7276595,0.0003920848,0.2492011,0.0007057018,0.0004106876,0.0001105391,0.006653857,0.001738988,0.01312761],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005401284,"threshold_uncertainty_score":0.01775587,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1362725403575334,"score_gpt":0.347717656344585,"score_spread":0.2114451159870515,"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."}}