{"id":"W2136180489","doi":"","title":"Phrase Clustering for Smoothing TM Probabilities - or, How to Extract Paraphrases from Phrase Tables","year":2010,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo; National Research Council Canada","funders":"","keywords":"Phrase; Smoothing; Computer science; Cluster analysis; Artificial intelligence; Natural language processing; Sentence; Machine translation; Language model; Feature (linguistics); Translation (biology); Linguistics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[0.002817456,0.00142932,0.0007188195,0.002638405,0.001083539,0.001533348,0.001647049,0.001383914,0.01648371],"category_scores_gemma":[0.01476712,0.0008316443,0.001288393,0.003007194,0.000711066,0.003654424,0.001584014,0.002574188,0.01274236],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005847249,"about_ca_system_score_gemma":0.001201941,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003092019,"about_ca_topic_score_gemma":0.00562531,"domain_scores_codex":[0.99844,0.000450959,0.0001563073,0.000434666,0.0004317468,0.00008639128],"domain_scores_gemma":[0.9963558,0.001459037,0.0002642557,0.001150827,0.0007104242,0.00005976859],"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":[0.0001733062,0.00007567245,0.001005152,0.000339131,0.0001312522,0.0001247573,0.0003759452,0.01680701,0.03186304,0.02094504,0.0229762,0.9051835],"study_design_scores_gemma":[0.0001105776,0.0001448251,0.003582695,0.000135264,0.0001797136,0.0008581545,0.0002696395,0.722709,0.1016591,0.08762341,0.08253083,0.0001967457],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001101139,0.0000796906,0.9944403,0.00005921537,0.00004641476,0.00005013762,0.0002001817,0.003536856,0.0004860551],"genre_scores_gemma":[0.02381505,0.0001742298,0.9718365,0.00008040073,0.00007503147,0.0001853869,0.0009277029,0.001303331,0.001602306],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01648371,"threshold_uncertainty_score":0.05514354,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02216712995711584,"score_gpt":0.2810010237187076,"score_spread":0.2588338937615917,"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."}}