{"id":"W4385573356","doi":"10.18653/v1/2022.emnlp-main.673","title":"Label-aware Multi-level Contrastive Learning for Cross-lingual Spoken Language Understanding","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"People's Government of Jilin Province; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Utterance; Benchmark (surveying); Natural language processing; Artificial intelligence; Context (archaeology); Word (group theory); Spoken language; Semantics (computer science); Code (set theory); Linguistics; Programming language","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":[0.0004993059,0.0001235734,0.000147638,0.00008726557,0.0006844492,0.0001819287,0.0005419528,0.00003339464,0.00009174491],"category_scores_gemma":[0.0001362355,0.0001267847,0.00005942177,0.0001729609,0.00002549581,0.0002359524,0.0004916444,0.0002633281,0.000005983592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002485006,"about_ca_system_score_gemma":0.00009209059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007396772,"about_ca_topic_score_gemma":0.00003398887,"domain_scores_codex":[0.9986887,0.00006124974,0.0001985289,0.0004286501,0.0002633291,0.0003595422],"domain_scores_gemma":[0.9992994,0.0003000516,0.00008007866,0.0002001443,0.00005288657,0.00006744792],"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":[0.0002571538,0.0006791517,0.02379333,0.000196051,0.0003587686,0.000380216,0.08993677,0.2339492,0.006279238,0.4741889,0.000811,0.1691703],"study_design_scores_gemma":[0.001743514,0.0001002647,0.0003349121,0.000009345163,0.000005305246,0.00001372626,0.006905532,0.9892282,0.000562827,0.0005505134,0.000326874,0.0002189222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06342213,0.000069396,0.9349319,0.0001782571,0.0003643987,0.0002591111,0.00001509498,0.000273845,0.0004859201],"genre_scores_gemma":[0.9366512,6.833822e-7,0.0584596,0.0002657384,0.00006899081,0.00004744592,0.000009978229,0.00001512842,0.004481208],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8764722,"threshold_uncertainty_score":0.5264299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.159149102394137,"score_gpt":0.3535188660146792,"score_spread":0.1943697636205422,"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."}}