{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004182781,0.0001074077,0.0001616631,0.0001311895,0.00002857336,0.00006274378,0.0007493094,0.00006493932,0.000005396723],"category_scores_gemma":[0.000244555,0.00008516038,0.00006547276,0.0002593912,0.00002852876,0.0004504359,0.000195739,0.00008447289,0.000003643472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004294404,"about_ca_system_score_gemma":0.00009031872,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000143777,"about_ca_topic_score_gemma":0.00001668448,"domain_scores_codex":[0.9991432,0.00002019104,0.0001773702,0.0002305001,0.0002027542,0.0002259422],"domain_scores_gemma":[0.9992706,0.00007007405,0.00009859023,0.0003779009,0.00009956493,0.00008328069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002845104,0.00005593661,0.00008681872,0.0001235172,0.00002074672,0.0000200782,0.01030236,0.00001531112,0.1453112,0.6509362,0.003359948,0.1897394],"study_design_scores_gemma":[0.0006538638,0.0002253813,0.000004930348,0.00005567153,0.000008441526,0.00002206051,0.001108021,0.01876832,0.9217787,0.05620841,0.0008994425,0.0002667297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03782671,0.001866726,0.9576501,0.0003277544,0.00008417427,0.0002073686,0.000002429018,0.0006209482,0.001413785],"genre_scores_gemma":[0.4505653,5.907817e-7,0.5488911,0.0001319072,0.0000251432,0.00001696554,0.000001373884,0.000007080111,0.0003605363],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7764675,"threshold_uncertainty_score":0.347274,"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."}}