{"id":"W3129054449","doi":"10.6180/jase.202106_24(3).0009","title":"Text Representation and Similarity Measure for Text Clustering Based on Semantic Strings: A Case Study on Uyghur Language","year":2021,"lang":"en","type":"article","venue":"Journal of Applied Science and Engineering","topic":"Advanced Computational Techniques and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Cluster analysis; Explicit semantic analysis; Text graph; String metric; Semantic similarity; String (physics); Text processing; Noisy text analytics; Word (group theory); Set (abstract data type); Representation (politics); Similarity (geometry); Language model; Information retrieval; String searching algorithm; Semantic computing; Text mining; Linguistics; Mathematics; Pattern matching; Semantic technology","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":[],"consensus_categories":[],"category_scores_codex":[0.0005063589,0.00008277119,0.0001186086,0.0001619334,0.0001761045,0.0001588513,0.0001658625,0.00001838265,2.701229e-7],"category_scores_gemma":[0.00008243322,0.00007462058,0.00002215425,0.0004585255,0.00002252548,0.0002181665,0.00006776637,0.0001218447,1.45989e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004181077,"about_ca_system_score_gemma":0.00006759821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001912206,"about_ca_topic_score_gemma":0.000002682368,"domain_scores_codex":[0.9991342,0.000005284074,0.0001816357,0.000231689,0.0003206852,0.0001264352],"domain_scores_gemma":[0.9993483,0.0001497185,0.00008788258,0.0001638897,0.0001688395,0.00008137267],"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":[0.00005487993,0.0003669921,0.0001364511,0.00009289533,0.00002786276,0.0008416991,0.004511247,0.7463459,0.1357359,0.01352899,0.00004127737,0.09831589],"study_design_scores_gemma":[0.0005666895,0.0002309062,0.001160891,0.0000602392,0.00001049391,0.0005544733,0.001304685,0.9853907,0.01005666,0.0004695119,0.00006287442,0.0001318817],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2995721,0.00001368571,0.6999161,0.0002231219,0.00003364623,0.0001490476,6.506898e-7,0.00002277707,0.00006888781],"genre_scores_gemma":[0.9334519,0.000001832747,0.06637608,0.0001142894,0.00003503626,0.00001412605,1.600907e-7,0.000004705675,0.000001863656],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6338798,"threshold_uncertainty_score":0.3042939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02359091826546359,"score_gpt":0.3016794827715407,"score_spread":0.2780885645060771,"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."}}