{"id":"W2141232148","doi":"10.3115/v1/w15-0915","title":"Building a Lexicon of Formulaic Language for Language Learners","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Lexicon; Computer science; Natural language processing; Identification (biology); Artificial intelligence; Recall; Computational linguistics; Linguistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00154659,0.00107639,0.0011142,0.002812057,0.0007799976,0.004128616,0.00182323,0.001268186,0.01032716],"category_scores_gemma":[0.01454158,0.001072622,0.001002542,0.002053687,0.0007745159,0.008593748,0.002956082,0.001789248,0.007835411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008984473,"about_ca_system_score_gemma":0.002905409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001776283,"about_ca_topic_score_gemma":0.002747446,"domain_scores_codex":[0.9986327,0.0003726786,0.0002161719,0.0003897642,0.000310665,0.00007788551],"domain_scores_gemma":[0.9932446,0.002617121,0.0003955506,0.001278693,0.00216226,0.0003016889],"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":[0.0002203669,0.0003981025,0.009972867,0.0008422165,0.0001041194,0.0005955945,0.003114022,0.008615481,0.0545265,0.04948732,0.01688805,0.8552354],"study_design_scores_gemma":[0.0002520877,0.001025431,0.009798798,0.0006331835,0.0004215643,0.002875259,0.006917272,0.4696936,0.1200665,0.2133218,0.1744795,0.0005149962],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05609623,0.000159514,0.922922,0.0004211474,0.000105315,0.0005061376,0.001916022,0.01070273,0.007170969],"genre_scores_gemma":[0.2205733,0.0002394121,0.7704062,0.0001651686,0.00004595761,0.0005919983,0.004451959,0.001106653,0.002419432],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01032716,"threshold_uncertainty_score":0.03454781,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02449955104441965,"score_gpt":0.3261592496904346,"score_spread":0.3016596986460149,"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."}}