{"id":"W2296383052","doi":"10.3115/v1/n15-1065","title":"Expanding Paraphrase Lexicons by Exploiting Lexical Variants","year":2015,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Paraphrase; Computer science; Natural language processing; Artificial intelligence; Linguistics","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":[0.0007688935,0.001115342,0.000889489,0.003878135,0.0005436761,0.00121166,0.001105044,0.000638623,0.003105677],"category_scores_gemma":[0.005348636,0.0007740182,0.001066693,0.002516204,0.0003905112,0.002674107,0.001787327,0.0008424886,0.00266695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003449984,"about_ca_system_score_gemma":0.0007453287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00150275,"about_ca_topic_score_gemma":0.003503981,"domain_scores_codex":[0.9990339,0.0002381302,0.0001305765,0.0003073624,0.000216494,0.00007351766],"domain_scores_gemma":[0.9974482,0.001229101,0.0002016169,0.0005700639,0.000483866,0.00006717272],"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":[0.0002249781,0.0002854536,0.006615083,0.0007229542,0.0001596722,0.001276327,0.001006275,0.01113221,0.1488522,0.005526284,0.008254082,0.8159444],"study_design_scores_gemma":[0.0002042061,0.0006799446,0.01740937,0.0002237089,0.0006406236,0.007701869,0.001433562,0.6805932,0.1973007,0.03422236,0.0594037,0.000186772],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2322031,0.001392395,0.7453859,0.0003590464,0.00007262333,0.000568575,0.001960405,0.01022802,0.007829939],"genre_scores_gemma":[0.5009867,0.0007175378,0.4843521,0.000202716,0.00009766203,0.0002357905,0.008925318,0.001288353,0.003193872],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003878135,"threshold_uncertainty_score":0.01038951,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09131101412097056,"score_gpt":0.3026592437913347,"score_spread":0.2113482296703641,"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."}}