{"id":"W3023872708","doi":"10.13025/htat-gw66","title":"Challenges of word sense alignment: Portuguese language resources","year":2020,"lang":"en","type":"article","venue":"Arrow@dit (Dublin Institute of Technology)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canadian Linguistic Association","funders":"Fundação para a Ciência e a Tecnologia; Ministério da Ciência, Tecnologia e Ensino Superior; Universidade Nova de Lisboa; European Commission","keywords":"Portuguese; Political science; European union; Brazilian Portuguese; Word (group theory); Library science; Linguistics; Sociology; Computer science; Business; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01579446,0.001000535,0.001584933,0.004932,0.004093496,0.009288014,0.002572255,0.001833002,0.002896136],"category_scores_gemma":[0.04362499,0.0008365151,0.0007450979,0.007513859,0.002646782,0.01222938,0.006395353,0.002313514,0.003083002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001934371,"about_ca_system_score_gemma":0.006371094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005671503,"about_ca_topic_score_gemma":0.006057648,"domain_scores_codex":[0.977783,0.01216906,0.00213482,0.002948989,0.004257699,0.0007063655],"domain_scores_gemma":[0.9669715,0.01953138,0.002415513,0.005598701,0.004652069,0.0008309244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003534062,0.0002412631,0.00403263,0.003971424,0.0001537273,0.002251279,0.01981989,0.007953016,0.02180633,0.1489184,0.03737839,0.7531202],"study_design_scores_gemma":[0.0000685336,0.0001435158,0.004911122,0.002647507,0.0001219139,0.003035061,0.04118828,0.0445023,0.03372434,0.3008676,0.5685381,0.000251725],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06596568,0.01093631,0.8564039,0.02386762,0.001281179,0.0005830169,0.003620471,0.005056086,0.03228577],"genre_scores_gemma":[0.3537089,0.007426936,0.6140786,0.002607346,0.000515388,0.0007123745,0.009043103,0.002846874,0.009060432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01579446,"threshold_uncertainty_score":0.08353007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02241459459780207,"score_gpt":0.2619537631504967,"score_spread":0.2395391685526946,"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."}}