{"id":"W3165505241","doi":"10.1145/3446678","title":"Two New Large Corpora for Vietnamese Aspect-based Sentiment Analysis at Sentence Level","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Benchmark (surveying); Vietnamese; Natural language processing; Artificial intelligence; Task (project management); Sentence; Deep learning; Sentiment analysis; Resource (disambiguation); Code (set theory); Linguistics","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":[0.001605819,0.0009333494,0.0005776467,0.003565905,0.001608688,0.001059076,0.001033309,0.0007030714,0.01707265],"category_scores_gemma":[0.00691853,0.000507144,0.0005140655,0.004691625,0.0007026363,0.001673126,0.001440907,0.001518556,0.006278974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009266409,"about_ca_system_score_gemma":0.001840034,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009724562,"about_ca_topic_score_gemma":0.0220233,"domain_scores_codex":[0.9984596,0.0003925388,0.000269833,0.0003452797,0.0004124779,0.0001203901],"domain_scores_gemma":[0.9917964,0.002206992,0.0005252098,0.001061992,0.003844962,0.0005644807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008462851,0.0009935794,0.016415,0.004300037,0.0001377084,0.002778401,0.008181942,0.003212485,0.06703721,0.01145931,0.5646141,0.320024],"study_design_scores_gemma":[0.0003330395,0.0004516998,0.106504,0.000494873,0.0001436114,0.002661366,0.004207536,0.0193002,0.03690002,0.005571743,0.8231493,0.0002826296],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.284348,0.002819658,0.0917147,0.002859634,0.002540393,0.003701837,0.5133112,0.01129882,0.08740575],"genre_scores_gemma":[0.1797985,0.0007699857,0.1303932,0.0005364417,0.0004301823,0.003942272,0.6633475,0.001924563,0.01885733],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01707265,"threshold_uncertainty_score":0.05711371,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01779395492959392,"score_gpt":0.2724116228654583,"score_spread":0.2546176679358644,"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."}}