{"id":"W4386005452","doi":"10.1007/978-3-031-37963-5_80","title":"Attention Is not Always What You Need: Towards Efficient Classification of Domain-Specific Text","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"ca_institutions":"IBM (Canada); Western University","funders":"","keywords":"Computer science; Artificial intelligence; Natural language processing; Classifier (UML); Jargon; Language model; Support vector machine; Question answering; Task (project management); Machine learning; Vectorization (mathematics); Domain (mathematical analysis); Linguistics; Mathematics","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":[0.001346181,0.00111346,0.001381461,0.002766492,0.000791799,0.002302853,0.00186014,0.001579277,0.004552521],"category_scores_gemma":[0.005295798,0.0004990479,0.001030251,0.003206602,0.0005667552,0.004251053,0.001950912,0.00206811,0.007832824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006822294,"about_ca_system_score_gemma":0.001129465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003554728,"about_ca_topic_score_gemma":0.00538633,"domain_scores_codex":[0.9990731,0.0002275718,0.00006347649,0.0002923833,0.000230736,0.0001126465],"domain_scores_gemma":[0.9967321,0.001817507,0.0001886002,0.0003643825,0.0007025065,0.0001949304],"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":[0.0002826771,0.000142391,0.00173253,0.0002897561,0.00006145921,0.00009722624,0.0003708333,0.004861447,0.01387649,0.004029579,0.06679635,0.9074591],"study_design_scores_gemma":[0.0000776641,0.0002449509,0.005849003,0.0001832646,0.000196364,0.0006108374,0.001130235,0.8339569,0.02532822,0.06403249,0.0683141,0.00007596761],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.08417981,0.01036707,0.8715907,0.003936022,0.0009396836,0.0003511461,0.005564691,0.0132487,0.009822249],"genre_scores_gemma":[0.301407,0.005528796,0.6324854,0.001238848,0.001606741,0.0004769428,0.02180364,0.001683765,0.03376881],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004552521,"threshold_uncertainty_score":0.0152297,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04058312260523922,"score_gpt":0.2389568133288028,"score_spread":0.1983736907235636,"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."}}