{"id":"W4393145735","doi":"10.1609/aaai.v38i21.30449","title":"Towards a Transformer-Based Reverse Dictionary Model for Quality Estimation of Definitions (Student Abstract)","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Transformer; Computer science; Quality (philosophy); Engineering; Electrical engineering; Philosophy","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":[0.003891075,0.0008070936,0.00111485,0.001838296,0.0003134455,0.002404152,0.002614179,0.001314075,0.004092854],"category_scores_gemma":[0.01955416,0.0006403768,0.001494622,0.001635642,0.001400338,0.005047226,0.002073159,0.002542995,0.001140304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001073185,"about_ca_system_score_gemma":0.001060097,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00805811,"about_ca_topic_score_gemma":0.007109136,"domain_scores_codex":[0.9982347,0.0007251566,0.000125795,0.0004849468,0.000273781,0.0001555544],"domain_scores_gemma":[0.9920654,0.00491006,0.000688264,0.0007865501,0.001282641,0.0002670261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000739423,0.0003418428,0.00946365,0.0003097174,0.0002527271,0.0002141947,0.0006514133,0.4527561,0.008498164,0.1797214,0.005029407,0.3420219],"study_design_scores_gemma":[0.000009334723,0.00003370133,0.0002529206,0.00000935051,0.00001187364,0.00002507288,0.00001644215,0.9744666,0.0004869736,0.02431046,0.0003685079,0.000008776037],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008740345,0.00009153606,0.9900601,0.0001674298,0.00001532989,0.00002960776,0.0000858675,0.0003157496,0.0004939674],"genre_scores_gemma":[0.5994962,0.0003531833,0.3956098,0.0002363833,0.00007119084,0.0001991732,0.0007050771,0.0002698856,0.003059151],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00805811,"threshold_uncertainty_score":0.02057827,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1585445641583282,"score_gpt":0.3841063597082742,"score_spread":0.225561795549946,"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."}}