{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003711751,0.0001029337,0.0001180201,0.0000539203,0.00008112951,0.0001730893,0.0005386877,0.00004964023,0.00003043923],"category_scores_gemma":[0.0000922305,0.00009242212,0.00003505941,0.000188681,0.00002015912,0.000621627,0.0002468915,0.0001056431,0.0001011797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003673728,"about_ca_system_score_gemma":0.00006366186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005759515,"about_ca_topic_score_gemma":0.000002661963,"domain_scores_codex":[0.9988326,0.00004666471,0.0002007374,0.0003511019,0.0002566616,0.0003122435],"domain_scores_gemma":[0.9991938,0.00006239746,0.00004010044,0.0004153616,0.00003709028,0.0002512722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001287501,0.0002595887,0.004870467,0.0000170129,0.00004680163,0.0001471999,0.00514378,0.0007822411,0.01089387,0.7847258,0.07187673,0.1212236],"study_design_scores_gemma":[0.001950469,0.0001364792,0.0002062957,0.00005934551,0.000009898737,0.0001205297,0.001316205,0.9115908,0.02220001,0.04871394,0.01278486,0.0009111761],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05779056,0.00008299762,0.9227862,0.001069539,0.000307274,0.00005760748,6.709505e-7,0.0002981151,0.01760706],"genre_scores_gemma":[0.8981307,0.000002532611,0.1002731,0.0007523321,0.00009695342,0.000008626501,0.00000112595,0.000006613249,0.0007280357],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9108086,"threshold_uncertainty_score":0.3768865,"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."}}