{"id":"W2950992105","doi":"10.48550/arxiv.1809.01446","title":"Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Parsing; Sanskrit; Segmentation; Artificial intelligence; Sentence; Word (group theory); Text segmentation; Task (project management); Graph; Context (archaeology); Mathematics; Linguistics; Theoretical computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004997791,0.000800497,0.0007140029,0.0005670781,0.0004932074,0.0009399416,0.001198107,0.001476301,0.002643374],"category_scores_gemma":[0.001044118,0.0005966031,0.0008248294,0.000537596,0.0005797835,0.001803781,0.0005360439,0.001257676,0.001089386],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000829066,"about_ca_system_score_gemma":0.0007866053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01780271,"about_ca_topic_score_gemma":0.04099388,"domain_scores_codex":[0.9998081,0.00005660801,0.00001004799,0.00008082904,0.00001893382,0.00002551895],"domain_scores_gemma":[0.9996401,0.0002080464,0.00003444031,0.0000360356,0.00005677987,0.00002467781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003533062,0.0001475586,0.003519291,0.00007980393,0.00007120431,0.0002711374,0.0002255349,0.9019132,0.007433137,0.01590386,0.00400872,0.06607328],"study_design_scores_gemma":[0.000003625709,0.000009655059,0.0002561295,0.000002699723,0.000005229881,0.0000137137,0.000006528312,0.9945139,0.0003271326,0.004648359,0.0002081816,0.000005016881],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.431749,0.001070868,0.5527831,0.002258275,0.0002072396,0.00008087625,0.001314624,0.003485185,0.007050877],"genre_scores_gemma":[0.9212789,0.0002930642,0.06531496,0.0002734354,0.00006914703,0.0001116803,0.001534488,0.0003641369,0.01076014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01780271,"threshold_uncertainty_score":0.03539819,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05503476004949358,"score_gpt":0.2268021652373592,"score_spread":0.1717674051878656,"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."}}