{"id":"W2892239351","doi":"10.18653/v1/d18-1276","title":"Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sanskrit; Word order; Computer science; Natural language processing; Word (group theory); Artificial intelligence; Text segmentation; Linguistics; Segmentation; Philosophy","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":[0.0003321267,0.0001201308,0.0001295655,0.0002116624,0.00005312667,0.0001267445,0.0007534521,0.0001071844,0.00001556583],"category_scores_gemma":[0.0001486156,0.0001037043,0.00001528588,0.0004087987,0.00006401013,0.0007013223,0.0002523503,0.00009768707,4.232276e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005285695,"about_ca_system_score_gemma":0.00005409389,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006575573,"about_ca_topic_score_gemma":0.003829456,"domain_scores_codex":[0.9989557,0.0000466024,0.0001916233,0.0004119627,0.0001437643,0.0002503039],"domain_scores_gemma":[0.9993252,0.00007431963,0.00004823473,0.0004265828,0.00007191511,0.00005379382],"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":[0.0001822468,0.0003680145,0.0009941193,0.0000561086,0.000006912854,0.00009472697,0.001903308,0.0009261451,0.02950433,0.1469774,0.004584501,0.8144022],"study_design_scores_gemma":[0.0005705837,0.000101924,0.0000426354,0.00002863899,0.000001205612,0.00000595942,0.00001723563,0.7766752,0.01627592,0.2060858,0.00006071523,0.0001342473],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02678322,0.0003039762,0.9700558,0.00220521,0.00003991771,0.0001495597,0.000003002769,0.0002873374,0.0001719996],"genre_scores_gemma":[0.3748037,0.000003960944,0.6232433,0.001770198,0.00002031368,0.00004246452,0.000003884611,0.00000581666,0.0001063192],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8142679,"threshold_uncertainty_score":0.4228938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02112711478314816,"score_gpt":0.2926867301244836,"score_spread":0.2715596153413354,"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."}}