{"id":"W2114562718","doi":"10.1613/jair.2784","title":"Complex Question Answering: Unsupervised Learning Approaches and Experiments","year":2009,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Lethbridge","keywords":"Automatic summarization; Set (abstract data type); Tree kernel; Weighting; Relevance (law); Unsupervised learning; ENCODE; Kernel (algebra); Feature (linguistics)","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003117866,0.00009454571,0.000179608,0.000366113,0.0002474312,0.0003598575,0.0006569347,0.00006004574,0.00001565298],"category_scores_gemma":[0.0003324164,0.0000834112,0.00005080249,0.0004223457,0.00009291626,0.0005909434,0.000131104,0.0006277038,0.00001175847],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007564771,"about_ca_system_score_gemma":0.00009456297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001975536,"about_ca_topic_score_gemma":0.000002064822,"domain_scores_codex":[0.997785,0.000353564,0.000498074,0.0002312426,0.0007809822,0.0003510946],"domain_scores_gemma":[0.9989751,0.0001576759,0.0001175213,0.0002094853,0.0003648656,0.000175379],"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":[0.00004446507,0.0001373647,0.0002115784,0.0000097293,0.00001085481,0.00003972688,0.003819064,0.007575038,0.03881267,0.08616489,0.00002542086,0.8631492],"study_design_scores_gemma":[0.0000521817,0.0008537101,0.0008585846,0.0000868584,0.000002642957,0.00008885657,0.002343809,0.8930392,0.05097654,0.05113424,0.0004143214,0.0001490117],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2151801,0.0003884833,0.7817964,0.001936042,0.0001007708,0.00009190699,6.573642e-8,0.00002166528,0.0004845936],"genre_scores_gemma":[0.9527923,0.00009432474,0.04685917,0.00002878244,0.0001881243,0.000001105211,1.91563e-7,0.000004632316,0.00003138765],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8854642,"threshold_uncertainty_score":0.3470114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4485195580979168,"score_gpt":0.4474377941188779,"score_spread":0.001081763979038919,"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."}}