{"id":"W2955319516","doi":"10.1075/itl.18033.bui","title":"Extracting multiword expressions from texts with the aid of online resources","year":2019,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Lexicography and Language Studies","field":"Arts and Humanities","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Victoria University; Victoria University of Wellington","keywords":"Vietnamese; Test (biology); Class (philosophy); Recall; Psychology; Linguistics; English as a foreign language; Word (group theory); Significant difference; Mathematics education; Computer science; Natural language processing; Artificial intelligence; Cognitive psychology; Mathematics","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":[0.0009615705,0.0005924262,0.000655117,0.001638454,0.0005594555,0.00142219,0.0007124402,0.0004381502,0.004441828],"category_scores_gemma":[0.005739524,0.0002021054,0.0002211784,0.001331694,0.0004548612,0.002024299,0.001330022,0.0004858567,0.001592041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003024683,"about_ca_system_score_gemma":0.0005568736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004471941,"about_ca_topic_score_gemma":0.000894115,"domain_scores_codex":[0.9991482,0.0003391152,0.00009119236,0.0002338742,0.0001410409,0.00004654711],"domain_scores_gemma":[0.9946985,0.003826124,0.0003693258,0.0004297722,0.0005417414,0.0001344126],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006311823,0.0009068837,0.007487988,0.001085773,0.00002880827,0.001044039,0.01100683,0.0003716667,0.1870821,0.0007375607,0.001738829,0.7878784],"study_design_scores_gemma":[0.0003812131,0.004573852,0.1329903,0.0007859641,0.0003654428,0.006070024,0.08011618,0.02474174,0.6556867,0.006772062,0.08725388,0.0002627676],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.9307762,0.0005642597,0.05989377,0.0003032618,0.0000698857,0.0005518661,0.0004945564,0.001040231,0.006305888],"genre_scores_gemma":[0.7944357,0.000750433,0.1993603,0.00008930002,0.00003472492,0.0002816235,0.0009525271,0.0001535977,0.003941644],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.004441828,"threshold_uncertainty_score":0.01485938,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01640013454175128,"score_gpt":0.2528442836995431,"score_spread":0.2364441491577919,"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."}}