{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002715777,0.0002070092,0.0002717394,0.0004792539,0.0006038231,0.0006147194,0.0003443814,0.00006555083,0.0002268571],"category_scores_gemma":[0.00003818132,0.0002000768,0.0002503034,0.001378209,0.0000265197,0.001032284,0.00003280245,0.0001357408,0.00003044923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000818396,"about_ca_system_score_gemma":0.0001470964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001710113,"about_ca_topic_score_gemma":0.00008948804,"domain_scores_codex":[0.9984533,0.0000458609,0.0004590089,0.0003316558,0.0003925044,0.0003176613],"domain_scores_gemma":[0.9987973,0.00006862088,0.0002746754,0.00053815,0.0001376209,0.0001836418],"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":[0.00009600146,0.0003300722,0.0007824018,0.0002678359,0.0006969546,0.0000254439,0.03736782,0.01862528,0.001200582,0.0006663552,0.0007429473,0.9391983],"study_design_scores_gemma":[0.00355352,0.00007131267,0.001014057,0.0002032309,0.0005543367,0.0000277392,0.01634705,0.9414389,0.02609161,0.0001017758,0.009952578,0.0006439138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009837416,0.0001943958,0.9866713,0.002287678,0.00005885495,0.0001584572,0.00003836281,0.0001253368,0.0006281699],"genre_scores_gemma":[0.895964,0.000006318792,0.09920857,0.002717314,0.00004691161,0.00002625478,0.0002513081,0.00001307603,0.001766264],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9385544,"threshold_uncertainty_score":0.8158897,"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."}}