{"id":"W3184501572","doi":"10.18653/v1/2021.starsem-1.29","title":"Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Natural language processing; Word (group theory); Artificial intelligence; Lexicon; Joint (building); Parallel corpora; Resource (disambiguation); Vocabulary; Extension (predicate logic); Machine translation; Linguistics; Programming language","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":[0.001123862,0.0002228666,0.0002772154,0.0001121361,0.0003308924,0.0007089415,0.0003485529,0.00008829693,0.00001008192],"category_scores_gemma":[0.0004703715,0.0001883959,0.00008703881,0.0002691157,0.00003719095,0.0008373678,0.0001624082,0.0003287466,0.000007981428],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006437973,"about_ca_system_score_gemma":0.0002269166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001755984,"about_ca_topic_score_gemma":0.000004915521,"domain_scores_codex":[0.9979941,0.00008373417,0.0004323082,0.0004873613,0.0005655702,0.0004369247],"domain_scores_gemma":[0.9987586,0.0001532713,0.0002846417,0.0004180991,0.000282769,0.0001025807],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008527984,0.00005059574,0.0008274294,0.00009321176,0.00003912483,0.00001202846,0.01598608,0.7410936,0.0008389506,0.01087543,0.00003607667,0.2300621],"study_design_scores_gemma":[0.001203209,0.0002837868,0.0002405668,0.0001007898,0.00001083665,0.0000584935,0.003059614,0.9920237,0.002103602,0.000202186,0.0004144821,0.0002987031],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3095445,0.00001991768,0.6851034,0.0001082278,0.00004878529,0.0002502471,7.813189e-7,0.0002523925,0.004671824],"genre_scores_gemma":[0.5403986,5.617679e-7,0.4586361,0.000376156,0.00007595721,0.00004279115,0.00002362805,0.00001253933,0.0004336997],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2509301,"threshold_uncertainty_score":0.7682563,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08097096599880486,"score_gpt":0.3404383184068583,"score_spread":0.2594673524080535,"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."}}