{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003465076,0.00007129684,0.00009821468,0.0002703415,0.00001810164,0.0000827456,0.0003678521,0.000033333,0.000001657271],"category_scores_gemma":[0.0001136666,0.00006204349,0.00002581426,0.0002003439,0.00001030188,0.003402238,0.00008607089,0.0001362379,4.58955e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009145351,"about_ca_system_score_gemma":0.00006935969,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001143362,"about_ca_topic_score_gemma":2.21054e-7,"domain_scores_codex":[0.9992052,0.000005906092,0.0003243898,0.00003118591,0.0002713343,0.0001620013],"domain_scores_gemma":[0.9990026,0.00002442638,0.0002849025,0.0000632974,0.000586806,0.00003799842],"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":[0.0001249968,0.0001203862,0.002846354,0.0005016793,0.0004128684,0.00002231242,0.005942322,0.129021,0.04055749,0.130448,0.0001796937,0.6898229],"study_design_scores_gemma":[0.0008434546,0.00007724829,0.002292827,0.000727661,0.00002647207,0.005212662,0.00008385104,0.934734,0.04541641,0.001465832,0.008701877,0.0004176752],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04521491,0.001186702,0.9528047,0.0002050404,0.0005149894,0.00002217155,5.166278e-7,0.00003426038,0.00001675351],"genre_scores_gemma":[0.8504052,0.00008256186,0.1493425,0.00004184437,0.0001223112,4.500843e-7,8.591628e-7,0.000002782813,0.0000014854],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.805713,"threshold_uncertainty_score":0.253006,"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."}}