{"id":"W3028435993","doi":"10.5220/0009422400580067","title":"Using BERT and XLNET for the Automatic Short Answer Grading Task","year":2020,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Task (project management); Grading (engineering); Artificial intelligence; Natural language processing; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001999507,0.002680717,0.001079166,0.003797912,0.0009380319,0.002011408,0.001281082,0.00247313,0.02325583],"category_scores_gemma":[0.008835179,0.0005136259,0.0009900366,0.002078759,0.0002021717,0.004444493,0.001666789,0.001991784,0.01394181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001246323,"about_ca_system_score_gemma":0.001915304,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01081814,"about_ca_topic_score_gemma":0.01921137,"domain_scores_codex":[0.998358,0.0005511103,0.0001377971,0.0004574617,0.0003105005,0.0001851503],"domain_scores_gemma":[0.9961811,0.001853762,0.0001731333,0.0003977248,0.001043299,0.0003510642],"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":[0.001567864,0.0007648197,0.007028206,0.0009763134,0.0001624518,0.0003642225,0.0003482765,0.00849463,0.02412427,0.00396666,0.1948144,0.757388],"study_design_scores_gemma":[0.0004432214,0.0009104557,0.01542826,0.0002547929,0.0002521287,0.0004552113,0.001083954,0.8087875,0.04018455,0.02261686,0.1094278,0.0001553242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2689721,0.0042633,0.3867345,0.004768397,0.003979323,0.001959791,0.07332273,0.2057277,0.05027207],"genre_scores_gemma":[0.5557544,0.0009981625,0.2389408,0.0009489546,0.001066795,0.001449634,0.1550158,0.003515574,0.04230992],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02325583,"threshold_uncertainty_score":0.07779849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1021931580915548,"score_gpt":0.294745850003279,"score_spread":0.1925526919117242,"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."}}