{"id":"W191017350","doi":"","title":"Enlarging Paraphrase Collections through Generalization and Instantiation","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Topic Modeling","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Japan Society for the Promotion of Science; National Research Council Canada","keywords":"Paraphrase; Computer science; Natural language processing; Generalization; Artificial intelligence; Quality (philosophy); Parallel corpora; Exploit; Machine translation; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"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":[0.0001098353,0.00004467049,0.00004462696,0.0000463269,0.0001875858,0.00007353117,0.00007871255,0.00002575574,0.0000169448],"category_scores_gemma":[0.00001777989,0.00004525776,0.00001086811,0.000284284,0.000008679672,0.0007703107,0.00004899452,0.00003553625,0.000004402469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001966177,"about_ca_system_score_gemma":0.0000147702,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001227746,"about_ca_topic_score_gemma":0.000003337006,"domain_scores_codex":[0.9995471,0.00002846242,0.00008551864,0.0001123324,0.00009156914,0.0001350687],"domain_scores_gemma":[0.999745,0.00001619896,0.00003035138,0.0001499214,0.00002275745,0.00003577362],"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":[0.000001536099,0.00004691369,0.01112317,0.000011367,0.00001083247,8.292962e-7,0.005444882,0.0007234493,0.0146698,0.9467589,0.001808592,0.01939971],"study_design_scores_gemma":[0.0005620639,0.00002737715,0.005596169,0.00002135196,0.00001459474,0.00003822537,0.0001198285,0.8903341,0.01265843,0.06400967,0.02629834,0.0003198951],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07691717,0.0001016821,0.9106861,0.0003427305,0.0002396789,0.0000564713,4.02097e-7,0.00007525244,0.01158055],"genre_scores_gemma":[0.8486709,0.00003349861,0.1508246,0.0002047722,0.00008383224,0.000006651805,0.000001200122,0.000002859587,0.0001716533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8896106,"threshold_uncertainty_score":0.1845558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02717435825852078,"score_gpt":0.255400939592151,"score_spread":0.2282265813336302,"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."}}