{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006666298,0.0002757435,0.0003710987,0.0004345858,0.0001506774,0.00008448374,0.001610578,0.000333514,0.000007772242],"category_scores_gemma":[0.001766796,0.0002652862,0.00009484293,0.001078921,0.0002522753,0.0008367553,0.0006660742,0.0003300651,0.00001453357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009721968,"about_ca_system_score_gemma":0.0003126944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002314239,"about_ca_topic_score_gemma":0.00001619221,"domain_scores_codex":[0.997705,0.00003140874,0.0005748663,0.0007815302,0.0005104065,0.0003968201],"domain_scores_gemma":[0.9981074,0.00005240785,0.0003765633,0.0009354064,0.0004195776,0.000108627],"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":[0.0001632478,0.0003235942,0.00007159236,0.0002980451,0.0001708611,0.0001391638,0.001364207,0.0004413809,0.09129648,0.1006146,0.02726366,0.7778531],"study_design_scores_gemma":[0.001818128,0.0004008384,0.000005149516,0.0001361011,0.00008178512,0.00005431474,0.0001210898,0.1020052,0.7596882,0.04488847,0.09024536,0.0005553098],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2441936,0.003849177,0.7156471,0.02775507,0.001544805,0.002908481,0.0008249119,0.003181074,0.00009578794],"genre_scores_gemma":[0.5127209,0.0000138948,0.4862863,0.0005055084,0.00009584097,0.0001096844,0.0002480231,0.00001397565,0.000005803664],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7772979,"threshold_uncertainty_score":0.9999799,"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."}}