{"id":"W2886776997","doi":"","title":"Leveraging Data Resources for Cross-Linguistic Information Retrieval Using Statistical Machine Translation","year":2018,"lang":"en","type":"article","venue":"Conference of the Association for Machine Translation in the Americas","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Machine translation; Computer science; Natural language processing; Rule-based machine translation; Artificial intelligence; Cross-language information retrieval; Translation (biology); Information retrieval","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":[0.002159649,0.0001512183,0.0002191964,0.0001304131,0.000338278,0.0003189013,0.001673347,0.00008705166,0.000004871484],"category_scores_gemma":[0.00216132,0.0001070889,0.00007039383,0.0005650372,0.0001239441,0.001020806,0.00008120337,0.000191609,9.764567e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009840319,"about_ca_system_score_gemma":0.0001079901,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001861698,"about_ca_topic_score_gemma":0.0000363207,"domain_scores_codex":[0.9982166,0.0002118908,0.0005911241,0.0002576295,0.0004879213,0.000234853],"domain_scores_gemma":[0.9967046,0.001360067,0.0007356852,0.0006226595,0.0005535983,0.00002336244],"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":[0.002112509,0.0004406938,0.03059646,0.0009843622,0.000322439,0.00000125622,0.1361142,0.002543921,0.0117348,0.1289508,0.0006741447,0.6855243],"study_design_scores_gemma":[0.0007872239,0.00009817788,0.002125079,0.00005405898,0.00005266399,0.000002715926,0.00005828268,0.9538046,0.00117903,0.03930948,0.002362261,0.0001664368],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004705928,0.000332191,0.9915693,0.001769052,0.0002339971,0.0007978778,0.0003366249,0.00008449691,0.0001704995],"genre_scores_gemma":[0.7717735,0.000004396991,0.2278123,0.000172525,0.00006877843,0.000008413726,0.0001414601,0.000007784654,0.00001085326],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9512607,"threshold_uncertainty_score":0.4366958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08431429977728597,"score_gpt":0.3712629859825227,"score_spread":0.2869486862052367,"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."}}