{"id":"W2051593977","doi":"10.1162/coli_a_00002","title":"Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":302,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Paraphrase; Computer science; Natural language processing; Task (project management); Artificial intelligence; Parallel corpora; Field (mathematics); Linguistics; Machine translation","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009106915,0.0001117199,0.0001713811,0.00008992578,0.000100893,0.0001286425,0.0008560031,0.00006489684,0.000003132662],"category_scores_gemma":[0.005156851,0.0001068044,0.00001775721,0.0002381548,0.0001128469,0.0001109758,0.00068984,0.000231343,9.01996e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005324181,"about_ca_system_score_gemma":0.0001478878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001245521,"about_ca_topic_score_gemma":0.00004658329,"domain_scores_codex":[0.9988407,0.0001435012,0.0002994914,0.00035194,0.0002324453,0.0001319322],"domain_scores_gemma":[0.9975768,0.0009368802,0.0001897044,0.0004174549,0.0008149914,0.00006417209],"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":[0.00004246154,0.0003656923,0.02046316,0.0002783426,0.0001873026,0.0000777918,0.001038516,0.0102211,0.02072168,0.6539841,0.002883636,0.2897362],"study_design_scores_gemma":[0.0001219476,0.00002117768,0.002478539,0.00001437184,0.000009153549,0.00001527037,0.000002057794,0.9685342,0.0007929353,0.02763526,0.0002445883,0.0001305059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008246019,0.0003009305,0.9905028,0.00002681942,0.0005927841,0.00007031312,0.00008251968,0.0001313574,0.00004646146],"genre_scores_gemma":[0.377103,0.000001573377,0.6225455,0.00005735033,0.0001508638,0.000001034156,0.0001318797,0.000005648833,0.000003121746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9583131,"threshold_uncertainty_score":0.6173605,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06410955906269462,"score_gpt":0.401568733933962,"score_spread":0.3374591748712674,"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."}}