{"id":"W2251141757","doi":"10.3115/v1/s14-1007","title":"Identifying semantic relations in a specialized corpus through distributional analysis of a cooccurrence tensor","year":2014,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Natural language processing; Tensor (intrinsic definition); Encoding (memory); Semantic space; Artificial intelligence; Space (punctuation); Word (group theory); Style (visual arts); Linguistics; Mathematics","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":[0.0003060175,0.00007224909,0.0002320702,0.0002022365,0.00005200181,0.0000479371,0.0003929721,0.00003530712,0.00008384925],"category_scores_gemma":[0.0001930593,0.00006762251,0.00009645253,0.001575476,0.00003509841,0.0003158638,0.0001281567,0.00007830954,0.00001680992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004198235,"about_ca_system_score_gemma":0.00004048989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003179933,"about_ca_topic_score_gemma":0.0002876634,"domain_scores_codex":[0.9988718,0.00007151809,0.0003651224,0.0002788763,0.0002577462,0.0001549274],"domain_scores_gemma":[0.9991863,0.0001902145,0.0001166817,0.0003896467,0.00008846945,0.00002873203],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002880094,0.00006327661,0.1021322,0.000009457916,0.00008182876,0.000002165025,0.0006627015,0.009280337,0.0003035656,0.8852029,0.00007488941,0.002183801],"study_design_scores_gemma":[0.0002315241,0.000006816088,0.1099464,0.00001864135,0.00005559683,0.000001277346,0.00001576127,0.8736088,0.0001200622,0.01566919,0.0002390857,0.00008688168],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09072744,0.00002390425,0.9071242,0.0002587645,0.000114096,0.00006318669,0.000005659208,0.00003911065,0.001643648],"genre_scores_gemma":[0.9335856,0.000003320853,0.06619955,0.00004516342,0.000018365,0.000004891769,0.00001109383,0.000001637932,0.0001303972],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8695337,"threshold_uncertainty_score":0.2757566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04415604225102656,"score_gpt":0.3008423448311019,"score_spread":0.2566863025800754,"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."}}