{"id":"W3160310472","doi":"10.32473/flairs.v34i1.128502","title":"Multilingual Automatic Term Extraction in Low-Resource Domains","year":2021,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Task (project management); Term (time); Artificial intelligence; Resource (disambiguation); Raw data; Sequence labeling; Sequence (biology); Domain (mathematical analysis); Artificial neural network; Natural language processing; Deep learning; Information extraction; Machine learning; Engineering","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":[0.002078337,0.0002041935,0.0002744965,0.0002221246,0.0002646479,0.0005162154,0.003189277,0.0001410629,0.00008844407],"category_scores_gemma":[0.001762214,0.0001790473,0.0003041015,0.001793862,0.000421635,0.001061137,0.001454756,0.0008989691,0.00002369183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004439155,"about_ca_system_score_gemma":0.0003974242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006845812,"about_ca_topic_score_gemma":0.00007803932,"domain_scores_codex":[0.9961391,0.00005852997,0.0007726431,0.0007010722,0.001793482,0.0005351656],"domain_scores_gemma":[0.9961059,0.000489856,0.0002878123,0.0003944755,0.002619711,0.0001022488],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002526952,0.0004802595,0.002578113,0.0001311717,0.0001084078,0.00001141271,0.006400238,0.0003392325,0.5017235,0.3444209,0.0005724651,0.1432091],"study_design_scores_gemma":[0.00003771513,0.00002352843,0.0005776777,0.0002894874,0.0000044572,0.00001096844,0.002612766,0.1910461,0.715722,0.08925138,0.0002695278,0.0001544012],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8505075,0.00008193103,0.1353222,0.006354816,0.0005591424,0.0005470475,0.0000080201,0.0002353244,0.006384049],"genre_scores_gemma":[0.9739368,0.000130608,0.02518836,0.00008563096,0.0001645121,0.00006448942,0.000002828893,0.00001411733,0.0004126522],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2551695,"threshold_uncertainty_score":0.7301338,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08710697055732607,"score_gpt":0.4004800386628963,"score_spread":0.3133730681055702,"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."}}