{"id":"W2938876272","doi":"10.5167/uzh-153213","title":"Exploiting alignment in multiparallel corpora for applications in linguistics and language learning","year":2018,"lang":"en","type":"dissertation","venue":"Zurich Open Repository and Archive (University of Zurich)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Atomic Energy of Canada Limited; University College London; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Linguistics; Applied linguistics; Corpus linguistics; Computer science; Natural language processing; Artificial intelligence; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004139789,0.0001543496,0.0002854519,0.0002459902,0.0002784528,0.00009945038,0.0007308377,0.0001061377,8.665365e-7],"category_scores_gemma":[0.0001109444,0.0001817545,0.00003170069,0.0001830419,0.0000666259,0.0001746983,0.0004228819,0.0002434305,3.22957e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003819723,"about_ca_system_score_gemma":0.00007377624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007503698,"about_ca_topic_score_gemma":0.000584331,"domain_scores_codex":[0.9989483,0.000139239,0.0001817183,0.0004563833,0.000112117,0.0001622271],"domain_scores_gemma":[0.9989622,0.0003561907,0.0003403997,0.0001976195,0.00008773489,0.00005589081],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00163973,0.001678938,0.0500715,0.007698048,0.0003824066,0.001176991,0.4259704,0.0001463391,0.07812962,0.2644199,0.003590744,0.1650954],"study_design_scores_gemma":[0.01730306,0.004219038,0.1198785,0.01558661,0.0007807706,0.0001682995,0.2498272,0.1354418,0.06422386,0.3146488,0.06869981,0.009222288],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.383723,0.004250709,0.5963762,0.00006307638,0.0002752009,0.003510984,0.00004050413,0.0002346226,0.01152565],"genre_scores_gemma":[0.3320257,0.00007733866,0.6662684,0.00000881191,0.00004150786,0.00001166834,0.00011679,0.00001325901,0.001436502],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.1761432,"threshold_uncertainty_score":0.7411733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01134433212542721,"score_gpt":0.2598633005983841,"score_spread":0.2485189684729569,"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."}}