{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006592654,0.001632903,0.001481311,0.005708662,0.002963914,0.005129666,0.001958036,0.001647363,0.009181509],"category_scores_gemma":[0.02537852,0.001691614,0.001788006,0.0101367,0.00211219,0.01232697,0.00609098,0.004161796,0.007799119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009846893,"about_ca_system_score_gemma":0.002266284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001227468,"about_ca_topic_score_gemma":0.002469881,"domain_scores_codex":[0.991438,0.004071116,0.0007482792,0.001977716,0.001518485,0.0002464397],"domain_scores_gemma":[0.9837901,0.008470118,0.001329366,0.004242432,0.001874644,0.0002933706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000376151,0.0003812181,0.003717964,0.001734357,0.0003161232,0.001198899,0.004534289,0.02256839,0.0352702,0.1117351,0.03062861,0.7875386],"study_design_scores_gemma":[0.0001456157,0.0002100439,0.005251793,0.000563731,0.0001810282,0.001178319,0.002742865,0.2445828,0.04144469,0.485063,0.2183924,0.0002437142],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01068827,0.001320624,0.9741278,0.001128164,0.0004378028,0.0002560742,0.001253921,0.004865348,0.005922012],"genre_scores_gemma":[0.05833889,0.00115943,0.927708,0.0002504986,0.0004011914,0.00056152,0.005841642,0.002095129,0.003643681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009181509,"threshold_uncertainty_score":0.03486568,"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."}}