{"id":"W4385573345","doi":"10.18653/v1/2022.nllp-1.30","title":"Computing and Exploiting Document Structure to Improve Unsupervised Extractive Summarization of Legal Case Decisions","year":2022,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Pittsburgh; National Science Foundation","keywords":"Automatic summarization; Computer science; Argumentative; Exploit; Representation (politics); Legal document; Artificial intelligence; Information retrieval; Ranking (information retrieval); Graph; Legal case; Domain (mathematical analysis); Data mining; Machine learning; Natural language processing; Theoretical computer science; Mathematics","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":[0.0002326612,0.0000855366,0.0001170565,0.0001065758,0.0002949134,0.00009329063,0.0002586857,0.000017617,0.00003490915],"category_scores_gemma":[0.00007452191,0.00008368384,0.00002262645,0.0002609531,0.000008356544,0.0003505007,0.0009454082,0.0001293607,3.093513e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006006597,"about_ca_system_score_gemma":0.00004904268,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000343391,"about_ca_topic_score_gemma":0.00003728595,"domain_scores_codex":[0.9989249,0.00006768972,0.0002514795,0.0003459882,0.0002521609,0.0001577517],"domain_scores_gemma":[0.9992942,0.0001989294,0.00007739869,0.00028575,0.00006712527,0.00007657243],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001884242,0.00005698205,0.0007492015,0.00001902655,0.0000316782,0.0003666409,0.01149063,0.09817476,0.04688908,0.1652808,0.00006502553,0.6768574],"study_design_scores_gemma":[0.0005097806,0.0001513697,0.0003864588,0.0000156618,0.000008146315,0.0005449957,0.003612167,0.9821151,0.008012659,0.004152826,0.0002662948,0.0002244747],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4542252,0.00001051386,0.5451689,0.0001775647,0.0001259281,0.0001270514,0.00000389639,0.00002875468,0.0001322361],"genre_scores_gemma":[0.8259056,4.477117e-7,0.1738496,0.0001701954,0.00002328925,0.000004836016,0.000001611113,0.000004666307,0.00003972526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8839404,"threshold_uncertainty_score":0.3412528,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0169936252046372,"score_gpt":0.2676518000611616,"score_spread":0.2506581748565244,"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."}}