{"id":"W2740290989","doi":"10.18653/v1/e17-2098","title":"Bootstrapping Unsupervised Bilingual Lexicon Induction","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Bootstrapping (finance); Computer science; Lexicon; Natural language processing; Artificial intelligence; Context (archaeology); Similarity (geometry); Task (project management); Basis (linear algebra); Speech recognition; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001194388,0.001021861,0.001209593,0.00184202,0.001047553,0.0008614632,0.001736685,0.0008394243,0.003934891],"category_scores_gemma":[0.0065485,0.0005776899,0.000999675,0.001933353,0.0009188976,0.002179323,0.00254162,0.001297593,0.003757864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005615202,"about_ca_system_score_gemma":0.001506955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001933247,"about_ca_topic_score_gemma":0.004939321,"domain_scores_codex":[0.9985138,0.0005779612,0.00007955038,0.0004133101,0.0002909102,0.0001245673],"domain_scores_gemma":[0.99687,0.001446867,0.0001807608,0.0008364091,0.000586895,0.00007910474],"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":[0.0003201571,0.0003010298,0.002776724,0.0003526871,0.0001668757,0.000455386,0.000426923,0.0388356,0.04090313,0.01433329,0.01844779,0.8826803],"study_design_scores_gemma":[0.0001448828,0.0001607952,0.002489237,0.00004360318,0.00008276435,0.0006259712,0.0002376122,0.8714167,0.04707047,0.06352021,0.01414576,0.00006207667],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04309649,0.000292408,0.9421199,0.000162624,0.00006993418,0.0002257725,0.0007527307,0.009261082,0.004019144],"genre_scores_gemma":[0.3963192,0.0002390421,0.5843065,0.0003256432,0.0001183975,0.0008471315,0.01123959,0.001361487,0.005243069],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003934891,"threshold_uncertainty_score":0.01316351,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03790606242258843,"score_gpt":0.3149337540185355,"score_spread":0.2770276915959471,"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."}}