{"id":"W4389519420","doi":"10.18653/v1/2023.emnlp-main.142","title":"A Diachronic Analysis of Paradigm Shifts in NLP Research: When, How, and Why?","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Deutsche Forschungsgemeinschaft","keywords":"Leverage (statistics); Computer science; Inference; Causal inference; Artificial intelligence; Field (mathematics); Data science; Natural language processing; Machine learning; 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":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.02129036,0.0005790303,0.0005209282,0.01528366,0.00355121,0.007393115,0.001541257,0.001404343,0.003361633],"category_scores_gemma":[0.1013758,0.0005817076,0.0008684935,0.01476648,0.005778257,0.01884445,0.00393334,0.003827882,0.0006455634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004211807,"about_ca_system_score_gemma":0.004449754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003197871,"about_ca_topic_score_gemma":0.004802217,"domain_scores_codex":[0.9888782,0.005385533,0.0008573183,0.002328077,0.002196994,0.0003538297],"domain_scores_gemma":[0.8674789,0.1035025,0.01316388,0.007480243,0.007087367,0.001287031],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002508796,0.0001865046,0.1325525,0.001303276,0.0001993146,0.0005406053,0.02217735,0.007257249,0.007484885,0.5196148,0.004889836,0.3035428],"study_design_scores_gemma":[0.00003807092,0.00008750488,0.06154862,0.0006585362,0.0001247407,0.0007561272,0.01203446,0.06112025,0.004995106,0.810462,0.04803076,0.0001438469],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.231833,0.007778958,0.7144098,0.01720399,0.0003211545,0.0005159496,0.002788338,0.000820959,0.02432778],"genre_scores_gemma":[0.8093728,0.002260935,0.1830544,0.000813933,0.0002606823,0.0004548123,0.001556014,0.0002092729,0.002017094],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9847164,"threshold_uncertainty_score":0.1125956,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1503477852821135,"score_gpt":0.3498817030182792,"score_spread":0.1995339177361657,"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."}}