{"id":"W2790484720","doi":"10.1109/ialp.2017.8300612","title":"Joint bi-affine parsing and semantic role labeling","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Parsing; Joint (building); Natural language processing; 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":[],"consensus_categories":[],"category_scores_codex":[0.0002084634,0.00007873763,0.00009989858,0.00005043266,0.0003487692,0.0007263285,0.0005706247,0.00003812904,0.000006219793],"category_scores_gemma":[0.0001063248,0.00006117387,0.00001662598,0.0000405756,0.0000407951,0.0006364982,0.0005402585,0.00009515053,0.000008203766],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001085656,"about_ca_system_score_gemma":0.00001491175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001343759,"about_ca_topic_score_gemma":0.0000187749,"domain_scores_codex":[0.9993914,0.00001040889,0.00009909993,0.0002285717,0.0001090807,0.0001613905],"domain_scores_gemma":[0.9992781,0.00001559525,0.00007696099,0.0005430619,0.00004077697,0.00004552645],"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":[0.000002439596,0.00003265188,0.001678298,0.00005878762,0.00001250329,0.0000552105,0.0007302701,0.000001425001,0.1465834,0.1112901,0.0006358234,0.7389191],"study_design_scores_gemma":[0.0005007922,0.00010005,0.003312004,0.0004047905,0.00001570521,0.0001618828,0.00004851109,0.1564814,0.564548,0.2720104,0.001731587,0.0006848411],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07643948,0.004797653,0.9026605,0.006869956,0.0002378113,0.000164794,4.455032e-7,0.001431373,0.007397952],"genre_scores_gemma":[0.576065,0.00001094171,0.4234821,0.0001464395,0.00002616395,0.000001110729,1.192401e-7,0.00000343,0.0002646479],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7382343,"threshold_uncertainty_score":0.7004002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01941539443293575,"score_gpt":0.2738629744058371,"score_spread":0.2544475799729013,"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."}}