{"id":"W2141656477","doi":"10.5815/ijieeb.2012.01.01","title":"Sentence Clustering Using Parts-of-Speech","year":2012,"lang":"en","type":"article","venue":"International Journal of Information Engineering and Electronic Business","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Cluster analysis; Syntax; Artificial intelligence; Natural language processing; Sentence; Hierarchical clustering; Brown clustering; Index (typography); Metric (unit); Similarity (geometry); Speech recognition; Fuzzy clustering; Canopy clustering algorithm","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":[0.001280071,0.001449563,0.001419179,0.0073355,0.001589244,0.001602484,0.001760197,0.001350236,0.00211748],"category_scores_gemma":[0.005246277,0.0004735446,0.001576466,0.004883719,0.001017437,0.001786761,0.001038384,0.0008342456,0.002450649],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008103796,"about_ca_system_score_gemma":0.001233164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003193344,"about_ca_topic_score_gemma":0.003258758,"domain_scores_codex":[0.9980234,0.0004519813,0.0001847167,0.0006425923,0.0006041555,0.00009315472],"domain_scores_gemma":[0.9970739,0.0009710865,0.00038769,0.000352984,0.001126648,0.00008764221],"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":[0.0006256081,0.0002672207,0.005194765,0.0008096375,0.0004556383,0.000618815,0.001862061,0.04693229,0.09985859,0.01263256,0.01128396,0.8194588],"study_design_scores_gemma":[0.00007452475,0.0003128156,0.01020587,0.0001316604,0.000431619,0.0009443759,0.001040835,0.8432192,0.07893032,0.04133676,0.0231548,0.000217253],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02939858,0.0007132349,0.9639266,0.0001733524,0.0001625478,0.000434116,0.0006500804,0.002975774,0.001565746],"genre_scores_gemma":[0.1683946,0.0004558454,0.8229108,0.0001269459,0.0002055918,0.000420746,0.003834578,0.0005945744,0.003056248],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0073355,"threshold_uncertainty_score":0.007083714,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007120919403451297,"score_gpt":0.2404078488024403,"score_spread":0.233286929398989,"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."}}