{"id":"W4280510965","doi":"10.18653/v1/2022.naacl-main.249","title":"On the Use of Bert for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Readability; Computer science; Representation (politics); Artificial intelligence; Scale (ratio); Set (abstract data type); Natural language processing; Transfer of learning; Task (project management); Feature learning; Joint (building); Deep learning; Domain (mathematical analysis); Machine learning; Multi-task learning; Programming language; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0006919513,0.0001700632,0.0003971935,0.0001766594,0.0004144453,0.00004247966,0.002259231,0.00004886855,0.000002345244],"category_scores_gemma":[0.009703887,0.0001043078,0.0002771601,0.000674832,0.00046045,0.00008255856,0.001277982,0.0003401067,5.560415e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001576294,"about_ca_system_score_gemma":0.0001091292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000154206,"about_ca_topic_score_gemma":0.00001752646,"domain_scores_codex":[0.9980643,0.00005853412,0.0006539768,0.0002761143,0.0007645942,0.0001824236],"domain_scores_gemma":[0.9929468,0.0008331428,0.003943073,0.0003689612,0.001896753,0.00001126385],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001777865,0.000528352,0.1163349,0.0007907745,0.0005704008,2.387773e-7,0.01557108,0.0549129,0.04928698,0.7528453,0.000811897,0.008169409],"study_design_scores_gemma":[0.001141027,0.0009870849,0.03196999,0.0005855911,0.0002804793,0.000003350127,0.005996218,0.4452435,0.3834261,0.1295892,0.0002188857,0.0005585247],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9712592,0.0001589189,0.02230383,0.002571513,0.0004300602,0.002143038,0.0003820821,0.0006194029,0.0001319786],"genre_scores_gemma":[0.9478335,0.000002487467,0.05182777,0.00003860539,0.00001417993,0.00008829202,0.000008024808,0.00001572125,0.0001713971],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6232561,"threshold_uncertainty_score":0.9986378,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04547728699506746,"score_gpt":0.2898841241251151,"score_spread":0.2444068371300476,"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."}}