{"id":"W1988834855","doi":"10.1002/meet.1450420170","title":"MARTT: Using induced knowledge base to automatically mark up plant taxonomic descriptions with XML","year":2005,"lang":"en","type":"article","venue":"Proceedings of the American Society for Information Science and Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Markup language; XML; Computer science; RuleML; Domain (mathematical analysis); Knowledge base; XHTML; Natural language processing; Artificial intelligence; Information retrieval; World Wide Web; 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":[0.001082237,0.0004834212,0.0003955701,0.002552559,0.0005007175,0.001264661,0.001469176,0.0007949474,0.003537841],"category_scores_gemma":[0.007067676,0.0003344584,0.0006874911,0.001391536,0.0003891722,0.002511779,0.001001214,0.0008702368,0.001356825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006811526,"about_ca_system_score_gemma":0.001056624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003517671,"about_ca_topic_score_gemma":0.004081715,"domain_scores_codex":[0.9992988,0.0002058845,0.00008421618,0.0001714913,0.0002135111,0.00002607224],"domain_scores_gemma":[0.9958113,0.002448686,0.0003934016,0.0006789259,0.0005852383,0.00008245806],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004170627,0.0004540356,0.003415151,0.0006844838,0.0001535377,0.0009576898,0.000609522,0.04868758,0.03108684,0.01231389,0.02459127,0.8766289],"study_design_scores_gemma":[0.00009346237,0.0002223921,0.002333499,0.0001481293,0.0001081836,0.0006500846,0.0003263615,0.8481215,0.09317507,0.01432124,0.04042437,0.00007582743],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06385507,0.0002445455,0.8713062,0.0004155302,0.0001333404,0.0003935221,0.00403233,0.05579398,0.003825406],"genre_scores_gemma":[0.1539906,0.0001956404,0.832621,0.0001661401,0.00003993435,0.0002609533,0.009682116,0.0005619057,0.002481695],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003537841,"threshold_uncertainty_score":0.01183522,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02088201374965352,"score_gpt":0.2770650099305437,"score_spread":0.2561829961808902,"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."}}