{"id":"W2164517999","doi":"10.1109/icassp.1996.540320","title":"Clustering words for statistical language models based on contextual word similarity","year":2002,"lang":"en","type":"article","venue":"","topic":"Speech Recognition and Synthesis","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"","keywords":"Perplexity; Computer science; Cluster analysis; Artificial intelligence; Word (group theory); Natural language processing; Similarity (geometry); Word error rate; Language model; Speech recognition; Mathematics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000171714,0.0001033751,0.0001309806,0.00007098641,0.00007874436,0.0001203172,0.0002785393,0.00004942518,0.0009962171],"category_scores_gemma":[0.0001223098,0.00008911222,0.00005729284,0.00009668087,0.00002307736,0.0001682774,0.00004292592,0.00007278031,0.00009057346],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002656746,"about_ca_system_score_gemma":0.000009991694,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001282485,"about_ca_topic_score_gemma":0.00004086746,"domain_scores_codex":[0.9991164,0.00004285988,0.0001479552,0.0002735163,0.0001930695,0.0002262498],"domain_scores_gemma":[0.9989337,0.0006279548,0.00002456578,0.0002734586,0.00003698218,0.0001032947],"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":[0.00002905324,0.0001994373,0.00000729389,0.00001612879,0.000009805222,0.00002647257,0.0004437123,0.0007780747,0.00005350936,0.02404019,0.007646072,0.9667503],"study_design_scores_gemma":[0.0004487032,0.00006341143,0.0000310766,0.00001142042,0.00000306788,0.000002131301,0.00006089536,0.9966967,0.000624719,0.001316589,0.0006117559,0.0001295774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006262175,0.000007773279,0.9653341,0.0009827848,0.0001083737,0.000167498,0.00002812862,0.0001909249,0.03255424],"genre_scores_gemma":[0.6279672,0.000001115814,0.3681112,0.002901663,0.00003538846,0.00002800739,0.00000358377,0.000007241268,0.0009446422],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9959186,"threshold_uncertainty_score":0.999917,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06789550791532689,"score_gpt":0.280999772124081,"score_spread":0.2131042642087541,"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."}}