{"id":"W2548230849","doi":"10.1075/nlp.2.15mey","title":"Extracting knowledge-rich contexts for terminography","year":2001,"lang":"en","type":"book-chapter","venue":"Natural language processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":215,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Construct (python library); Computer science; Paralanguage; Domain knowledge; Domain (mathematical analysis); Knowledge extraction; Field (mathematics); Context (archaeology); Knowledge management; Natural language processing; Data science; Artificial intelligence; Psychology; Communication; Geography; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005306258,0.0009565764,0.0008628641,0.0008096725,0.0005663479,0.0009534777,0.002333633,0.0008533777,0.00003822714],"category_scores_gemma":[0.0002527835,0.0008446428,0.0004477105,0.0003492268,0.0001530006,0.001422905,0.00053997,0.001680204,0.00003280994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002219155,"about_ca_system_score_gemma":0.0003137696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000832424,"about_ca_topic_score_gemma":0.00002862515,"domain_scores_codex":[0.996295,0.00003278453,0.0007794738,0.001414361,0.0005919903,0.0008863951],"domain_scores_gemma":[0.9968852,0.0003504634,0.0009378355,0.0008897218,0.0007469194,0.0001898201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000021406,0.00002721694,0.000003450084,0.0006022839,0.00004492642,0.0001559541,0.001538779,1.678437e-7,0.0006345861,0.01322338,0.00146435,0.9822835],"study_design_scores_gemma":[0.004744011,0.0008412653,0.00002128007,0.01851698,0.0009517972,0.003311776,0.0005417956,0.06881844,0.0217189,0.1768467,0.6901055,0.01358155],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.00002119715,0.6957977,0.1205934,0.0002826504,0.0009542715,0.00108584,0.00002610611,0.002822111,0.1784167],"genre_scores_gemma":[0.1843339,0.0001739035,0.467833,0.0008167608,0.001707481,0.0001355013,0.0001582562,0.0003025974,0.3445386],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.968702,"threshold_uncertainty_score":0.9994004,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01563003246822913,"score_gpt":0.3028685290154244,"score_spread":0.2872384965471953,"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."}}