{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006865417,0.0003695306,0.0006122225,0.0002972099,0.00009395431,0.0004142936,0.0005374936,0.000662361,0.000005724658],"category_scores_gemma":[0.000008215933,0.0003280517,0.0001505287,0.0001920336,0.00006968564,0.0001414082,0.0002108591,0.0005042474,0.0000124613],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001200015,"about_ca_system_score_gemma":0.00003946412,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000531457,"about_ca_topic_score_gemma":0.00001965082,"domain_scores_codex":[0.9974149,0.00006644204,0.0008042768,0.0008349387,0.0005425942,0.0003368547],"domain_scores_gemma":[0.9982219,0.0002086301,0.0004661447,0.0008922443,0.0001336968,0.00007735604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002444546,0.00002476552,0.00008934597,0.0003630376,0.00007858172,0.00002507099,0.001919103,0.3621461,0.0002420361,0.2930494,0.000314204,0.3417238],"study_design_scores_gemma":[0.0003028779,0.00005247436,0.0003162663,0.001705677,0.00001600494,0.00001921512,0.00004854273,0.976543,0.00001269075,0.004582399,0.01597318,0.0004276659],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000654346,0.01002598,0.9813073,0.000660881,0.003753208,0.000595333,0.000007440136,0.0001030259,0.002892483],"genre_scores_gemma":[0.9859712,0.004501178,0.002850825,0.0002059146,0.001466823,0.00005037002,0.00005833798,0.00009825538,0.004797104],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9853169,"threshold_uncertainty_score":0.9999171,"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."}}