{"id":"W2921492024","doi":"10.17169/refubium-1361","title":"Multiword expressions at length and in depth","year":2018,"lang":"en","type":"preprint","venue":"BiblioBoard Library Catalog (Open Research Library)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Killam Trusts","keywords":"Computer science; Linguistics; Mathematics; Philosophy","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001352668,0.001398525,0.0008631657,0.001764513,0.002000199,0.008262293,0.001232108,0.001567707,0.02942729],"category_scores_gemma":[0.006080576,0.0009154886,0.001059643,0.003251839,0.002128893,0.01520573,0.0040651,0.005857308,0.01564088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00154335,"about_ca_system_score_gemma":0.001528169,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001232083,"about_ca_topic_score_gemma":0.002063446,"domain_scores_codex":[0.9980407,0.0006991878,0.0001717746,0.0003214931,0.0006589635,0.0001078196],"domain_scores_gemma":[0.998095,0.0008916689,0.0001167822,0.0003323548,0.0004902171,0.00007390662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001256526,0.00004446068,0.0004780339,0.001064475,0.00005733172,0.0004248005,0.0072719,0.001127966,0.009219567,0.557223,0.1327714,0.2901916],"study_design_scores_gemma":[0.000006301796,0.0000187097,0.0004524164,0.000520928,0.00002379686,0.000556417,0.001797587,0.003317333,0.004031234,0.2081186,0.7811233,0.0000332911],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01411298,0.03601409,0.693038,0.02633621,0.008617773,0.0002740056,0.002540631,0.004081124,0.2149852],"genre_scores_gemma":[0.2231479,0.03164421,0.3773992,0.0065531,0.00483356,0.0006169516,0.007444202,0.008859507,0.3395015],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.02942729,"threshold_uncertainty_score":0.0984441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08918085580013325,"score_gpt":0.3745387782391162,"score_spread":0.285357922438983,"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."}}