{"id":"W4240238853","doi":"10.1139/geomatica-2018-0007","title":"A cyclic self-learning Chinese word segmentation for the geoscience domain","year":2020,"lang":"en","type":"article","venue":"GEOMATICA","topic":"Drilling and Well Engineering","field":"Engineering","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Domain (mathematical analysis); Context (archaeology); Benchmark (surveying); Text segmentation; Natural language processing; Segmentation; Artificial intelligence; Word (group theory); Information retrieval; Earth science; Geography; Archaeology; Geology; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005272982,0.001622246,0.001293291,0.002786879,0.00115472,0.0008610947,0.001774071,0.001327983,0.00898143],"category_scores_gemma":[0.001427854,0.0004668621,0.001172837,0.003043065,0.0005821788,0.002271716,0.001679706,0.001315215,0.003764718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007832394,"about_ca_system_score_gemma":0.00287223,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02054148,"about_ca_topic_score_gemma":0.02787217,"domain_scores_codex":[0.9993299,0.00007685238,0.00006179344,0.0003281686,0.0001095994,0.00009361978],"domain_scores_gemma":[0.9989451,0.0003565537,0.00004869443,0.0001676302,0.0003796506,0.0001024821],"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":[0.0007823224,0.0003666769,0.002036216,0.0003265279,0.00009455379,0.0003593945,0.0002093706,0.01209091,0.03416527,0.002791398,0.02172693,0.9250504],"study_design_scores_gemma":[0.0002052457,0.0005340643,0.003421896,0.00005150096,0.0001558015,0.0003752253,0.0004380611,0.9395322,0.0311463,0.008540372,0.01552507,0.00007440011],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2244787,0.002803647,0.7300429,0.0006407913,0.0008343204,0.0005378551,0.005264141,0.02570616,0.009691568],"genre_scores_gemma":[0.362238,0.0008191129,0.5969971,0.0005298248,0.0002985646,0.0003932248,0.02208281,0.001282961,0.0153585],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02054148,"threshold_uncertainty_score":0.04084384,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00596136852586742,"score_gpt":0.1995657127775393,"score_spread":0.1936043442516718,"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."}}