{"id":"W2407557870","doi":"10.63317/2ccdwd2a9gnc","title":"Detection of Domain Specific Terminology Using Corpora Comparison","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Terminology; Computer science; Term (time); Identification (biology); Focus (optics); Natural language processing; Task (project management); Domain (mathematical analysis); Artificial intelligence; Field (mathematics); Lexicography; Selection (genetic algorithm); Information retrieval; Linguistics","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":[0.005242655,0.0009584689,0.001188094,0.01933405,0.0016246,0.003543354,0.001254145,0.001254035,0.004282401],"category_scores_gemma":[0.02966842,0.0004379955,0.0009172987,0.01716569,0.0008569057,0.004109313,0.002234647,0.0009850824,0.002375994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008689847,"about_ca_system_score_gemma":0.001587992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001575757,"about_ca_topic_score_gemma":0.001885481,"domain_scores_codex":[0.992392,0.002507667,0.001213445,0.001849861,0.00175203,0.0002849783],"domain_scores_gemma":[0.9762439,0.01141712,0.002388632,0.002690016,0.006800422,0.0004598866],"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":[0.0009275998,0.0002612061,0.02593225,0.002355893,0.0003503193,0.002271064,0.005382216,0.003987128,0.1102845,0.01468544,0.0157923,0.81777],"study_design_scores_gemma":[0.0005768486,0.001701478,0.163897,0.001125697,0.002065396,0.01301062,0.01359235,0.1431728,0.2622555,0.04722323,0.3507496,0.0006295039],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4697714,0.007643201,0.4699016,0.0008963371,0.0007715495,0.002168436,0.008463549,0.00830904,0.03207493],"genre_scores_gemma":[0.4543787,0.002038195,0.5186516,0.000211792,0.0003317252,0.001420947,0.01630706,0.001350086,0.005309953],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01933405,"threshold_uncertainty_score":0.02772617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03402595291646539,"score_gpt":0.2916037686252727,"score_spread":0.2575778157088073,"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."}}