{"id":"W1828724394","doi":"10.48550/arxiv.1410.2455","title":"BilBOWA: Fast Bilingual Distributed Representations without Word Alignments","year":2014,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":314,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Task (project management); Word (group theory); Bilingual dictionary; Sentence; Feature (linguistics); Set (abstract data type); Machine translation; Translation (biology); Speech recognition; Linguistics","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":[0.0001829446,0.0001318348,0.0001397734,0.0001116436,0.000181415,0.00007516473,0.0008402623,0.00005904865,0.00001806863],"category_scores_gemma":[0.00006976611,0.000143886,0.00007029923,0.0005975176,0.00005891147,0.0004588038,0.000344497,0.0001150594,0.0000991214],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007713546,"about_ca_system_score_gemma":0.00005928318,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009956973,"about_ca_topic_score_gemma":0.00003988825,"domain_scores_codex":[0.9987322,0.0001029069,0.0001457446,0.0006425263,0.000094295,0.000282333],"domain_scores_gemma":[0.998716,0.00008301009,0.0000910437,0.0008870688,0.00007930151,0.0001435747],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002254927,0.0001831455,0.1035267,0.00001643886,0.00007913289,0.0001051387,0.0007319194,0.2228393,0.0005693646,0.6628449,0.0004153918,0.008665971],"study_design_scores_gemma":[0.0006595714,0.00003224093,0.004775782,0.00001550576,0.00002057868,0.000005056323,0.0001392401,0.9774767,0.0004346395,0.01470086,0.001494785,0.0002451024],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3392994,0.000002789021,0.658565,0.0000942191,0.0001641755,0.0000744604,0.000003462505,0.000154247,0.001642256],"genre_scores_gemma":[0.9936779,0.000004804222,0.004770947,0.00009224128,0.00005858924,3.74515e-7,0.000008809771,0.000007509233,0.001378846],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7546373,"threshold_uncertainty_score":0.5867503,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0557204607827267,"score_gpt":0.2038580054545029,"score_spread":0.1481375446717763,"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."}}