{"id":"W4389519299","doi":"10.18653/v1/2023.nllp-1.24","title":"AsyLex: A Dataset for Legal Language Processing of Refugee Claims","year":2023,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Inference; Artificial intelligence; Task (project management); Named-entity recognition; Set (abstract data type); Process (computing); Annotation; Refugee; Legal case; Comprehension; Domain (mathematical analysis); Information extraction; Data science; Information retrieval; Machine learning; Law; Political science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007818851,0.00005498033,0.0001090695,0.00005739063,0.0002780211,0.00005563337,0.0002653441,0.00005912236,0.0002877882],"category_scores_gemma":[0.0003508588,0.00004937121,0.00003822704,0.0004395561,0.0002672083,0.0002833688,0.00004306165,0.00004739976,0.0001468809],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000251462,"about_ca_system_score_gemma":0.0001419849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002551605,"about_ca_topic_score_gemma":0.007130997,"domain_scores_codex":[0.9991025,0.00003927223,0.000191451,0.0001560964,0.0002418978,0.0002687612],"domain_scores_gemma":[0.9995022,0.000165054,0.00006375968,0.0001421696,0.0000713938,0.0000553852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006382885,0.00009601628,0.0004208429,0.0001244792,0.00002195935,0.00001464041,0.02942757,0.00006558245,0.006946695,0.5498073,0.2225395,0.1904716],"study_design_scores_gemma":[0.00006259711,0.00005129062,0.00005235202,0.00003136939,0.0000132086,3.462915e-7,0.03379732,0.001795003,0.01736799,0.007218804,0.9394453,0.0001644865],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.752291,0.0003183112,0.0181437,0.01374701,0.001687477,0.00289258,0.004248932,0.001491484,0.2051795],"genre_scores_gemma":[0.9913473,0.000006860868,0.001602948,0.0001855556,0.000250886,0.00002897759,0.0002938631,0.000010946,0.006272697],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7169057,"threshold_uncertainty_score":0.3979264,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08610100527460676,"score_gpt":0.457051905237411,"score_spread":0.3709508999628043,"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."}}