{"id":"W2895115809","doi":"10.1145/3209280.3229100","title":"Automatic Term Extraction in Technical Domain using Part-of-Speech and Common-Word Features","year":2018,"lang":"en","type":"article","venue":"","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Terminology; Term (time); Domain (mathematical analysis); Confusion; Technical documentation; Documentation; Key (lock); Natural language processing; Ambiguity; Artificial intelligence; Information retrieval; Word (group theory); Speech recognition; Programming language; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003239706,0.0001098216,0.0002194125,0.00022061,0.00006121784,0.00005296579,0.0003516468,0.00008716277,0.00001925463],"category_scores_gemma":[0.00003002489,0.00009397733,0.00003610177,0.0005180302,0.0001533591,0.0004933347,0.0002156685,0.0001359459,0.0000021339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005517159,"about_ca_system_score_gemma":0.0000188948,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007863386,"about_ca_topic_score_gemma":0.0004925153,"domain_scores_codex":[0.9990144,0.00006141725,0.0002944831,0.0002740418,0.0001802945,0.0001753481],"domain_scores_gemma":[0.9992344,0.00009859985,0.0001244673,0.0004575785,0.00004331729,0.00004163996],"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":[0.000008574971,0.0001514177,0.01368456,0.00003381806,0.0000192032,0.00003519397,0.0004189313,0.000006514137,0.1201096,0.03577922,0.0003763963,0.8293766],"study_design_scores_gemma":[0.0009401056,0.0004710611,0.2578562,0.0005145289,0.00004963838,0.0006513793,0.000125514,0.178467,0.3263222,0.2315018,0.002010643,0.001089802],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.504366,0.00003941881,0.493938,0.0001561817,0.00003786834,0.0001289672,2.267521e-7,0.0002894106,0.001043997],"genre_scores_gemma":[0.5537058,0.000005582859,0.4462053,0.00003297918,0.00002294894,0.00000384937,2.914445e-7,0.000003795044,0.00001938884],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8282868,"threshold_uncertainty_score":0.3832284,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02079483283180173,"score_gpt":0.3401692492987932,"score_spread":0.3193744164669915,"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."}}