{"id":"W2044810048","doi":"10.1002/asi.22696","title":"Mining a multilingual association dictionary from<scp>W</scp>ikipedia for cross‐language information retrieval","year":2012,"lang":"en","type":"article","venue":"Journal of the American Society for Information Science and Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"York University","funders":"","keywords":"Computer science; Cross-language information retrieval; Information retrieval; Variety (cybernetics); Association (psychology); Natural language processing; Graph; Artificial intelligence; Machine translation; Quality (philosophy); Query expansion; Meaning (existential); Filter (signal processing)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009390027,0.0006499853,0.0007487804,0.009555426,0.001393519,0.001780054,0.001046986,0.0007682618,0.004865533],"category_scores_gemma":[0.006239666,0.0004259156,0.0009102265,0.009223473,0.0007107035,0.003859299,0.002704048,0.001144398,0.003570253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006374907,"about_ca_system_score_gemma":0.002199291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003291576,"about_ca_topic_score_gemma":0.009737184,"domain_scores_codex":[0.9986649,0.0002420363,0.0002669437,0.0003882899,0.0003379332,0.000099973],"domain_scores_gemma":[0.9964154,0.001186043,0.0004624274,0.0007630453,0.0009867747,0.0001863975],"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":[0.0003318582,0.0004570108,0.01406396,0.001896188,0.0002753361,0.002083391,0.002013336,0.006713036,0.0577641,0.02976946,0.06539703,0.8192352],"study_design_scores_gemma":[0.0001716112,0.0005528037,0.03044448,0.0006165406,0.000454916,0.005312777,0.006260121,0.212411,0.06054725,0.08914154,0.5937719,0.000315167],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1406727,0.002413887,0.8026677,0.001492331,0.0005314418,0.0008639428,0.02451294,0.006198061,0.02064693],"genre_scores_gemma":[0.2851179,0.001655281,0.6440409,0.0005278143,0.0002080123,0.0007919393,0.05873458,0.0008033426,0.008120308],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009555426,"threshold_uncertainty_score":0.01627684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008604640807155386,"score_gpt":0.2943862322322477,"score_spread":0.2857815914250924,"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."}}