{"id":"W2103759455","doi":"","title":"AUTOMATIC TERM EXTRACTION AND DOCUMENT SIMILARITY IN SPECIAL TEXT CORPORA","year":2003,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Term (time); Natural language processing; Collocation (remote sensing); Artificial intelligence; Similarity (geometry); Representation (politics); Information retrieval; Word (group theory); Lexical analysis; Text corpus; Vocabulary; Vector space model; Terminology; Computational linguistics; Linguistics; Machine learning","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":[0.005196194,0.001172181,0.002343194,0.01931899,0.001473125,0.003491417,0.001855076,0.001436653,0.003370708],"category_scores_gemma":[0.03516073,0.000695196,0.001898504,0.01658746,0.0008843758,0.005695658,0.002456046,0.001301495,0.003651605],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001307516,"about_ca_system_score_gemma":0.001352831,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001913607,"about_ca_topic_score_gemma":0.00196226,"domain_scores_codex":[0.9904675,0.002598345,0.001578145,0.002004863,0.002988066,0.0003630052],"domain_scores_gemma":[0.9760049,0.01280706,0.002427423,0.003217816,0.005277606,0.0002652542],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0006958409,0.0002739255,0.006403803,0.001526788,0.0003180153,0.0005658649,0.0008045807,0.01196835,0.05181452,0.009736365,0.01767194,0.89822],"study_design_scores_gemma":[0.000372011,0.001036071,0.04916751,0.0003695052,0.0006082605,0.003653364,0.001611507,0.6489211,0.1553571,0.04888774,0.0895791,0.0004367455],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1564354,0.005673448,0.8043711,0.0005865732,0.0005908013,0.001169581,0.006905863,0.01641623,0.007850917],"genre_scores_gemma":[0.2336931,0.001374146,0.7373987,0.0001119671,0.0003716633,0.001201859,0.02069496,0.0009450014,0.004208607],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01931899,"threshold_uncertainty_score":0.02748048,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0114018642908061,"score_gpt":0.2793095136083764,"score_spread":0.2679076493175703,"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."}}