{"id":"W3022934019","doi":"10.13025/29462","title":"A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment","year":2020,"lang":"en","type":"article","venue":"Arrow@dit (Dublin Institute of Technology)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canarie","funders":"Irish Research Council; Science Foundation Ireland; European Commission","keywords":"Word (group theory); Natural language processing; Computer science; Word-sense disambiguation; Linguistics; Artificial intelligence","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":[0.003485028,0.002450375,0.001432337,0.007158222,0.00220443,0.001953665,0.00314091,0.00223686,0.0159469],"category_scores_gemma":[0.009921432,0.0005548412,0.001542513,0.00553618,0.001004948,0.003722158,0.004614912,0.001837715,0.02643409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001785965,"about_ca_system_score_gemma":0.002913737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01366539,"about_ca_topic_score_gemma":0.03336049,"domain_scores_codex":[0.9952153,0.001233395,0.000822324,0.001171615,0.001215152,0.0003422676],"domain_scores_gemma":[0.9937511,0.001399112,0.000475488,0.001730544,0.001996697,0.0006469603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008254541,0.0007783909,0.007409488,0.002600031,0.0003024805,0.0004505185,0.0005220358,0.001898062,0.007532252,0.004304336,0.8998101,0.07356684],"study_design_scores_gemma":[0.001013775,0.0005721188,0.03536629,0.0007050454,0.0002186554,0.001556274,0.002145433,0.01859593,0.01355138,0.007145904,0.9188892,0.0002401689],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.039436,0.001432067,0.00786995,0.000659438,0.0005686189,0.0007515102,0.9189061,0.009689941,0.02068642],"genre_scores_gemma":[0.0094413,0.0001178728,0.01048065,0.0001281198,0.00002562848,0.0004488915,0.9769995,0.0002924251,0.002065571],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0159469,"threshold_uncertainty_score":0.05334771,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04416201849000012,"score_gpt":0.3289890192432291,"score_spread":0.284827000753229,"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."}}