{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003053753,0.0002151349,0.0002372582,0.0002814365,0.00006971751,0.0004239376,0.001426006,0.0001890802,0.0009143468],"category_scores_gemma":[0.00002346854,0.000225877,0.00004008927,0.0003991229,0.00002155704,0.0006232296,0.0006192724,0.0003334063,0.00134192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000228543,"about_ca_system_score_gemma":0.00009068785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002644178,"about_ca_topic_score_gemma":0.01074182,"domain_scores_codex":[0.9983428,0.00008806842,0.0003162643,0.0006961718,0.0002847913,0.0002719239],"domain_scores_gemma":[0.9987771,0.0001002287,0.0002776922,0.00075643,0.0000346323,0.00005394069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000212819,0.0002605818,0.0001941465,0.00004685293,0.0001446846,0.0001069139,0.007433574,0.001459117,0.008917006,0.001025088,0.6273236,0.3530672],"study_design_scores_gemma":[0.0008261171,0.00005485918,0.0003970056,0.002349117,0.00003987332,0.00001377219,0.0006608452,0.7653908,0.00234536,0.0005920741,0.226317,0.001013144],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.001852492,0.0003625446,0.4862023,0.00242011,0.001220629,0.001258607,0.0002521778,0.0001341238,0.506297],"genre_scores_gemma":[0.03103209,0.00007130313,0.1608994,0.0002687574,0.0002875986,0.0002164149,0.0003673997,0.0004966948,0.8063603],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.7639317,"threshold_uncertainty_score":0.9999989,"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."}}