{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001899769,0.001187017,0.000697009,0.001043441,0.0003517004,0.001200088,0.00102615,0.001051225,0.002070007],"category_scores_gemma":[0.006633693,0.0002450959,0.0003048739,0.001107598,0.0005045083,0.003204202,0.001572664,0.001791451,0.001134397],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005842492,"about_ca_system_score_gemma":0.0005885134,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001508849,"about_ca_topic_score_gemma":0.002535606,"domain_scores_codex":[0.9991537,0.0003887652,0.00004946074,0.0001984902,0.0001476555,0.00006190292],"domain_scores_gemma":[0.9977602,0.0009326489,0.0002722894,0.0004562018,0.0004166677,0.000162038],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0005871914,0.0003563367,0.005710181,0.0001162445,0.00007644324,0.0001267331,0.000187544,0.09183167,0.01068141,0.00709103,0.008812601,0.8744226],"study_design_scores_gemma":[0.00002141359,0.0001380789,0.001519252,0.0000149598,0.00001280429,0.00005611491,0.00004667038,0.985759,0.00358811,0.007015782,0.0018077,0.00002016241],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1963626,0.001382658,0.786039,0.001251422,0.0002923417,0.0001824196,0.0006674331,0.007029141,0.006792959],"genre_scores_gemma":[0.8749508,0.0004006062,0.1158601,0.0001953352,0.0001485642,0.0001061642,0.001297581,0.0001329834,0.006907944],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002070007,"threshold_uncertainty_score":0.01004702,"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."}}