{"id":"W2125268123","doi":"","title":"From the Definitions of the \"Trésor de la Langue Française\" To a Semantic Database of the French Language","year":2010,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Lexicon; Lexical database; Semantics (computer science); Natural language processing; XML; Artificial intelligence; Meaning (existential); Information retrieval; WordNet; World Wide Web; Programming language","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0006071589,0.000210227,0.0002446118,0.00005557457,0.0001314956,0.0001082992,0.005454246,0.0002487852,0.00007384726],"category_scores_gemma":[0.0006973551,0.00009449432,0.0001956857,0.0003937048,0.0002370838,0.00007701472,0.005075272,0.001227679,0.000005364095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002046625,"about_ca_system_score_gemma":0.0002934089,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03042379,"about_ca_topic_score_gemma":0.004270984,"domain_scores_codex":[0.9983848,0.0003133942,0.0003004303,0.0003799447,0.0004192572,0.0002021329],"domain_scores_gemma":[0.9958302,0.000769159,0.0002791274,0.00295633,0.0001182878,0.00004687758],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001948532,0.0007794676,0.006595563,0.001020411,0.0003568247,0.00005961281,0.1024214,0.0001453243,0.4477952,0.3072813,0.1100227,0.0235027],"study_design_scores_gemma":[0.0003787042,0.00003229126,0.01759379,0.002776746,0.0002325317,0.00005124598,0.0006675537,0.004771917,0.7151247,0.2559168,0.001662319,0.0007913465],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4309756,0.004794502,0.538272,0.01458723,0.001199735,0.001704907,0.001440156,0.000660823,0.0063651],"genre_scores_gemma":[0.750383,0.00001116282,0.2485027,0.0008406424,0.00008657726,0.00004537545,0.00001296517,0.0000132812,0.0001043047],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3194075,"threshold_uncertainty_score":0.9999267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01554731210509607,"score_gpt":0.2775662658126556,"score_spread":0.2620189537075595,"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."}}