{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001372822,0.001198294,0.0011988,0.001922521,0.0006925612,0.001347272,0.001617107,0.0009570955,0.002825406],"category_scores_gemma":[0.006564256,0.0006381816,0.00164912,0.001357855,0.00070272,0.002271668,0.0009459872,0.001184757,0.00263979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009209368,"about_ca_system_score_gemma":0.0009591395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005023876,"about_ca_topic_score_gemma":0.007049322,"domain_scores_codex":[0.998551,0.0005739523,0.0001169499,0.0003345736,0.0003561239,0.00006746134],"domain_scores_gemma":[0.9979789,0.001263711,0.0001319963,0.0002455981,0.0003363817,0.00004349028],"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":[0.0003179908,0.0001272523,0.001934418,0.0004673577,0.0004565307,0.0001869356,0.0005307088,0.4343723,0.01815964,0.06689782,0.004016239,0.4725328],"study_design_scores_gemma":[0.00001258855,0.00004945682,0.0002367023,0.00001765899,0.00004162589,0.00004783796,0.0000387584,0.9629553,0.002060799,0.03220764,0.002304469,0.00002728013],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005377369,0.0001509288,0.9932857,0.00004227559,0.00002207759,0.00005243345,0.00008612984,0.0007218898,0.0002611967],"genre_scores_gemma":[0.1537468,0.0005401495,0.8404165,0.0001322599,0.0001417014,0.000557637,0.001612416,0.0007790228,0.002073648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005023876,"threshold_uncertainty_score":0.009989262,"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."}}