{"id":"W2562276887","doi":"10.71781/11124","title":"From Word Embeddings to Large Vocabulary Neural Machine Translation","year":2015,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Samsung; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Word (group theory); Translation (biology); Machine translation; Computer science; Natural language processing; Vocabulary; Artificial intelligence; Speech recognition; Linguistics; Biology; 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":[0.001030161,0.001296169,0.0008156286,0.001329559,0.0004617993,0.001755849,0.001225111,0.001240652,0.01021012],"category_scores_gemma":[0.006662867,0.0006123325,0.0009665066,0.002142861,0.0006242418,0.004394528,0.001863035,0.00166542,0.003993069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000743985,"about_ca_system_score_gemma":0.0009628944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003854951,"about_ca_topic_score_gemma":0.006758209,"domain_scores_codex":[0.9991044,0.000350336,0.00007441839,0.0002455426,0.0001549215,0.00007031748],"domain_scores_gemma":[0.9979025,0.001060501,0.000120678,0.0005516748,0.0003198633,0.00004483132],"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":[0.0003779492,0.0001638235,0.0009869066,0.0004898357,0.0001603002,0.0002345209,0.000215137,0.08985279,0.01168735,0.04673017,0.01329462,0.8358067],"study_design_scores_gemma":[0.00007514749,0.000160109,0.0007399461,0.00007363268,0.00005579706,0.0001792655,0.0001727591,0.8265895,0.01083791,0.1462345,0.01484209,0.00003932987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03633996,0.001742561,0.9447089,0.0007848817,0.0004373823,0.000133269,0.001142227,0.006720482,0.007990393],"genre_scores_gemma":[0.4461737,0.001780616,0.5217845,0.0004454241,0.0003854255,0.000403826,0.005107828,0.0009180892,0.02300071],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01021012,"threshold_uncertainty_score":0.03415626,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03084650420625809,"score_gpt":0.357611872142071,"score_spread":0.3267653679358129,"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."}}