{"id":"W2886752202","doi":"10.1139/geomat-2018-0007","title":"A cyclic self-learning Chinese word segmentation for the geoscience domain","year":2018,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Computer science; Context (archaeology); Domain (mathematical analysis); Benchmark (surveying); Natural language processing; Text segmentation; Segmentation; Word (group theory); Artificial intelligence; Information retrieval; Geography; Archaeology; Linguistics; Cartography","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005614239,0.00008776268,0.00008151996,0.00004077261,0.0004809031,0.0001885178,0.0007214846,0.00002524081,0.00001594179],"category_scores_gemma":[0.0001492893,0.0000564825,0.00003949444,0.0002944607,0.0000662681,0.0002815804,0.0001716054,0.00006785554,0.0000791624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002657211,"about_ca_system_score_gemma":0.00003404927,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001395644,"about_ca_topic_score_gemma":0.000009602623,"domain_scores_codex":[0.9990466,0.00004618235,0.000172219,0.0002540699,0.0002216554,0.000259315],"domain_scores_gemma":[0.9990669,0.0003344077,0.00007907131,0.0004166014,0.00005740506,0.00004557493],"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":[0.00002747827,0.0002204879,0.005668269,0.0001728877,0.0001168554,0.000007493196,0.07661025,0.01333194,0.008645955,0.1092255,0.0008004805,0.7851724],"study_design_scores_gemma":[0.0001847698,0.0000505325,0.002847862,0.00001082422,0.000004791795,0.000005975278,0.0001292524,0.9751033,0.0001045533,0.01874437,0.002721793,0.00009196232],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1509255,0.0000213815,0.8465463,0.00136279,0.000268736,0.000269066,3.161291e-7,0.0001706699,0.0004352246],"genre_scores_gemma":[0.6076499,0.000001830665,0.3917061,0.0002851172,0.0001537524,0.00005573342,3.834748e-7,0.000004403486,0.0001427184],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9617714,"threshold_uncertainty_score":0.3698766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0110331818280587,"score_gpt":0.2655054943658863,"score_spread":0.2544723125378276,"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."}}