{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01047882,0.001759898,0.002634373,0.007297795,0.0009583142,0.0034426,0.005062104,0.001920267,0.003921885],"category_scores_gemma":[0.03765097,0.001163737,0.00169058,0.009864944,0.001401756,0.005885391,0.002230366,0.002093506,0.003457798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009461999,"about_ca_system_score_gemma":0.001856804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001743503,"about_ca_topic_score_gemma":0.002342924,"domain_scores_codex":[0.9888002,0.005245849,0.001435808,0.001457733,0.002913964,0.0001464791],"domain_scores_gemma":[0.9483508,0.03835462,0.001861513,0.004715962,0.006364801,0.0003522425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001780643,0.0003150378,0.001234041,0.00376138,0.000109724,0.0001086523,0.0006247784,0.00402025,0.007104069,0.006241766,0.005496593,0.9708057],"study_design_scores_gemma":[0.0006051477,0.001691794,0.01181951,0.00417152,0.00088692,0.006003825,0.004444236,0.4604189,0.1392234,0.1208381,0.2492936,0.0006031058],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01209397,0.0309357,0.943764,0.001370584,0.0001220495,0.0009578547,0.002346252,0.004271593,0.004137907],"genre_scores_gemma":[0.05460917,0.01910826,0.9149152,0.0004581482,0.000162799,0.0008902143,0.007204855,0.0008128833,0.001838503],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.01047882,"threshold_uncertainty_score":0.05541795,"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."}}