{"id":"W4385386988","doi":"10.18280/ria.370320","title":"Evaluation of Short Answers Using Domain Specific Embedding and Siamese Stacked BiLSTM with Contrastive Loss","year":2023,"lang":"en","type":"article","venue":"Revue d intelligence artificielle","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Domain (mathematical analysis); Embedding; Computer science; Artificial intelligence; Natural language processing; Linguistics; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001843985,0.001096518,0.0006517696,0.000750791,0.000218701,0.0009343201,0.0007734207,0.001250967,0.003141096],"category_scores_gemma":[0.004644134,0.0001506254,0.0004793591,0.0003424632,0.0002488605,0.001364323,0.0007917379,0.0009389807,0.001259028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006786524,"about_ca_system_score_gemma":0.0006178643,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003412583,"about_ca_topic_score_gemma":0.005568378,"domain_scores_codex":[0.9988725,0.00036525,0.00009772691,0.0002499367,0.0003249803,0.00008962787],"domain_scores_gemma":[0.9984046,0.0005870517,0.0001287844,0.0001335908,0.0006407317,0.0001053085],"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":[0.001976655,0.001046813,0.01288305,0.0005793154,0.0003906875,0.0004701768,0.0002573603,0.106287,0.06970417,0.001273451,0.01276557,0.7923657],"study_design_scores_gemma":[0.00005406867,0.001340779,0.006043701,0.00003827518,0.00006115867,0.000151166,0.000153034,0.952709,0.03639396,0.00096822,0.002056458,0.00003018619],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7312872,0.002458424,0.2453412,0.0007667518,0.0005170471,0.0003607637,0.00201878,0.009339738,0.007910127],"genre_scores_gemma":[0.9239681,0.0003459351,0.06447392,0.0001682025,0.00006270934,0.0001483229,0.004014313,0.0001161183,0.006702371],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003412583,"threshold_uncertainty_score":0.01050806,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1025520882371787,"score_gpt":0.3313457783093441,"score_spread":0.2287936900721654,"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."}}