{"id":"W2146546639","doi":"","title":"Learning Bigrams from Unigrams","year":2008,"lang":"en","type":"article","venue":"Meeting of the Association for Computational Linguistics","topic":"Topic Modeling","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bigram; Perplexity; Computer science; Language model; Natural language processing; Artificial intelligence; Word (group theory); Trigram; Oracle; Set (abstract data type); Speech recognition; Mathematics; Programming language","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0004997115,0.0000860983,0.0001456079,0.00004260376,0.0003854272,0.00003823262,0.0005293936,0.00006326164,6.484752e-7],"category_scores_gemma":[0.008465158,0.00007786802,0.0001219603,0.000220848,0.00002130962,0.00002987542,0.0001419479,0.0001377924,0.000003884287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001264315,"about_ca_system_score_gemma":0.0001070811,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001042024,"about_ca_topic_score_gemma":0.000005143499,"domain_scores_codex":[0.9987119,0.00009312051,0.0003462097,0.0001954529,0.0004927404,0.000160614],"domain_scores_gemma":[0.9969376,0.001429117,0.0005488979,0.0001808242,0.0008743603,0.00002917531],"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":[0.000003377751,0.00003773203,0.08573426,0.000009505736,0.0000509084,4.885418e-7,0.001133965,0.8445374,0.0000396203,0.0671602,0.0004813809,0.0008112015],"study_design_scores_gemma":[0.0003314731,0.00002674421,0.01265597,0.00003600351,0.00001507661,6.524019e-7,0.00002167378,0.9194275,0.0002571492,0.05800137,0.009110992,0.0001154303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1152335,0.00005555198,0.8779747,0.0006009102,0.002156079,0.0002231491,0.00002382695,0.0001749083,0.003557381],"genre_scores_gemma":[0.8257209,0.000001755787,0.1734126,0.00008479365,0.0003273247,0.000003964496,0.00002049721,0.00000770738,0.000420408],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7104874,"threshold_uncertainty_score":0.999887,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02239389677370867,"score_gpt":0.2445550466316511,"score_spread":0.2221611498579424,"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."}}