{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001483375,0.002047314,0.001175224,0.01087647,0.001079944,0.001672572,0.001160876,0.001544416,0.004197982],"category_scores_gemma":[0.008540659,0.000497544,0.001398726,0.005721747,0.000561023,0.002506081,0.001381328,0.001280278,0.005070153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006624972,"about_ca_system_score_gemma":0.002029525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002969169,"about_ca_topic_score_gemma":0.003779588,"domain_scores_codex":[0.9978414,0.0004135069,0.0004477506,0.0005385902,0.0006409317,0.0001178933],"domain_scores_gemma":[0.992479,0.003948049,0.0006863445,0.000721311,0.002028831,0.0001365219],"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":[0.0002954806,0.0001574725,0.002851748,0.002059604,0.0001113848,0.001345615,0.0008406907,0.004042848,0.2060095,0.004882738,0.02273452,0.7546684],"study_design_scores_gemma":[0.0002106884,0.0005408635,0.028429,0.0005867878,0.0005693694,0.007418093,0.001897109,0.3317086,0.4287089,0.02295839,0.1765738,0.0003983427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05252789,0.002275012,0.9085377,0.0004929344,0.0003421801,0.0006782924,0.009692616,0.02062927,0.004824043],"genre_scores_gemma":[0.1016741,0.0009724888,0.8698932,0.0001453768,0.0001407877,0.0005094245,0.02158337,0.001128892,0.003952327],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01087647,"threshold_uncertainty_score":0.01404363,"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."}}