{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007816349,0.00104487,0.0007370647,0.003630168,0.0005391437,0.001193649,0.00135007,0.0006573736,0.003072514],"category_scores_gemma":[0.005436913,0.0007088809,0.001262239,0.002448246,0.0006769381,0.002837973,0.001998859,0.001007807,0.001701921],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004732434,"about_ca_system_score_gemma":0.0007053522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001309374,"about_ca_topic_score_gemma":0.00450177,"domain_scores_codex":[0.9990109,0.0002176586,0.0001169694,0.0003412673,0.0002442394,0.00006893322],"domain_scores_gemma":[0.9969855,0.001396754,0.0002511373,0.0008126962,0.0004742593,0.00007968773],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002627692,0.0004735316,0.01110579,0.0007540233,0.0002175344,0.002001778,0.001645694,0.02003577,0.1422267,0.01466465,0.01011765,0.7964941],"study_design_scores_gemma":[0.0001952714,0.000760098,0.02748396,0.0002324015,0.0006779254,0.006276843,0.001824383,0.6952996,0.09870922,0.1071804,0.06118694,0.0001730274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2723053,0.0009190823,0.701885,0.0005373427,0.00006360601,0.0008539609,0.002438542,0.008368419,0.0126287],"genre_scores_gemma":[0.558216,0.0007281955,0.426327,0.0002871388,0.00009626707,0.0004159731,0.009966584,0.0007309787,0.003231979],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003630168,"threshold_uncertainty_score":0.01027852,"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."}}