{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000275395,0.00008088085,0.00009052857,0.00009177229,0.00004179028,0.0001675762,0.0001899011,0.00005227332,0.00010726],"category_scores_gemma":[0.00005674993,0.00006728368,0.00001312158,0.0001967923,0.00002277458,0.0006145191,0.00006507397,0.0001279195,0.00000763184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005964174,"about_ca_system_score_gemma":0.00003098109,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000259952,"about_ca_topic_score_gemma":0.00004563847,"domain_scores_codex":[0.9993184,0.00004725702,0.000145878,0.0002157401,0.0001382558,0.0001345255],"domain_scores_gemma":[0.9996581,0.00003910342,0.00005535246,0.0001902546,0.00001908053,0.0000380977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003155022,0.00009009821,0.005281232,0.00005590922,0.000004557443,0.0001005483,0.0006861417,8.562795e-7,0.003086491,0.4184602,0.00159421,0.5706366],"study_design_scores_gemma":[0.0006987157,0.0001259966,0.02394045,0.0001099352,0.000006556918,0.0002423347,0.00005503514,0.01090582,0.07381395,0.8867913,0.002737204,0.0005727101],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2376776,0.0009360431,0.7354873,0.00130559,0.00059635,0.0005530491,4.816737e-7,0.001264182,0.02217946],"genre_scores_gemma":[0.5326203,0.000006348951,0.4670516,0.0001425779,0.00002912131,0.00000482747,2.306688e-7,0.000002410103,0.0001426325],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5700639,"threshold_uncertainty_score":0.2743748,"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."}}