{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001927199,0.00008916443,0.00008449148,0.00007102343,0.0004076097,0.000692148,0.001346427,0.00007197672,0.00001604389],"category_scores_gemma":[0.0001253264,0.00007247346,0.00003398302,0.00006319791,0.00005295436,0.001280184,0.000306235,0.0001465994,0.00001832812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002287732,"about_ca_system_score_gemma":0.00008712243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000118911,"about_ca_topic_score_gemma":0.00001826424,"domain_scores_codex":[0.9992709,0.00001512707,0.0001141921,0.0002763289,0.0001529682,0.000170484],"domain_scores_gemma":[0.9989361,0.00001369914,0.00009065421,0.0008478321,0.00006622127,0.0000455461],"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":[0.000004424763,0.00004106672,0.0007999704,0.00002642424,0.00001254932,0.00003322979,0.0005788831,0.000002488397,0.09810969,0.4163723,0.0005482783,0.4834706],"study_design_scores_gemma":[0.0003937412,0.00009386017,0.002419087,0.00009061184,0.000005832865,0.00006556281,0.00005903151,0.01891697,0.7631322,0.2123633,0.0019434,0.000516379],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05654229,0.0003387982,0.9275987,0.002881533,0.0004882595,0.0001283388,2.959051e-7,0.001521866,0.01049995],"genre_scores_gemma":[0.7488754,0.000003640665,0.2504059,0.0001621291,0.00008312479,0.000002511792,4.311377e-7,0.000004365213,0.0004625609],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6923331,"threshold_uncertainty_score":0.6674399,"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."}}