{"id":"W2792210162","doi":"10.1145/3160488","title":"Expanding Paraphrase Lexicons by Exploiting Generalities","year":2018,"lang":"en","type":"article","venue":"ACM Transactions on Asian and Low-Resource Language Information Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"Japan Society for the Promotion of Science","keywords":"Paraphrase; Computer science; Natural language processing; Lexicon; Artificial intelligence; Leverage (statistics); Task (project management); Substitution (logic); Set (abstract data type); Semantic equivalence","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":[0.0002648619,0.0002433932,0.0001791731,0.0003721497,0.0008394205,0.0009655566,0.0006416353,0.0001253736,0.00004804618],"category_scores_gemma":[0.0000777981,0.0002240189,0.00005539541,0.0005167248,0.0001629716,0.003594194,0.00003776569,0.000307651,0.00002579341],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005352883,"about_ca_system_score_gemma":0.00005080636,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002145399,"about_ca_topic_score_gemma":0.000005702892,"domain_scores_codex":[0.998585,0.00005184411,0.0003995179,0.0002728177,0.0003162943,0.0003745],"domain_scores_gemma":[0.9990337,0.0000570157,0.0002101583,0.0004602238,0.0000974963,0.0001413348],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001525035,0.00002779811,0.000006781557,0.0001122504,0.00001123451,0.00000390815,0.03143599,0.000007909453,0.003387899,0.000426556,0.0004344261,0.96413],"study_design_scores_gemma":[0.002220419,0.0004815373,0.00003708145,0.001689972,0.00006786072,0.0003986507,0.05933669,0.04364179,0.8642846,0.005670622,0.02002742,0.002143365],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02070392,0.0008830702,0.9735418,0.001359917,0.00006903638,0.0001679711,0.00001817722,0.001052214,0.002203921],"genre_scores_gemma":[0.873732,0.00001120705,0.1232411,0.002652537,0.00007338414,0.00003620804,0.00002219495,0.00001584077,0.0002156057],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9619867,"threshold_uncertainty_score":0.9310884,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00916648332078006,"score_gpt":0.2578009485067484,"score_spread":0.2486344651859683,"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."}}