{"id":"W2573843450","doi":"","title":"Determining the Multiword Expression Inventory of a Surprise Language","year":2016,"lang":"en","type":"article","venue":"International Conference on Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Treebank; Surprise; Computer science; Natural language processing; Identification (biology); Artificial intelligence; Language model; Natural language; Language identification; Parsing; Psychology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002191178,0.000125285,0.0001128475,0.0001269511,0.00007054997,0.00008185847,0.001191561,0.00004998885,0.00003251286],"category_scores_gemma":[0.002139311,0.0000734663,0.00005369971,0.0000984055,0.0001014001,0.00009272188,0.0002521072,0.0001212665,0.00001433972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000574611,"about_ca_system_score_gemma":0.0001183376,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006458141,"about_ca_topic_score_gemma":0.000002199749,"domain_scores_codex":[0.9986998,0.00006121897,0.0002933827,0.0002482406,0.0005703074,0.0001269837],"domain_scores_gemma":[0.997772,0.0005335349,0.0002508408,0.0002502586,0.001149473,0.00004391434],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002664753,0.0001019881,0.001889922,0.00001083715,0.00002027529,0.00001545569,0.0006722093,0.0001445761,0.003139485,0.9438444,0.0006967584,0.04943741],"study_design_scores_gemma":[0.002037121,0.0003213213,0.004696784,0.001592598,0.00001774523,0.00001557641,0.0001678546,0.2896415,0.05728692,0.6397289,0.003693107,0.0008005159],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01883386,0.00007440431,0.9717624,0.001314298,0.001342886,0.0001657983,0.00004402789,0.0002513844,0.006210985],"genre_scores_gemma":[0.8409463,0.000004571024,0.1584935,0.0002104541,0.0001789644,0.000007973231,0.000009281038,0.000007226874,0.0001417214],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8221124,"threshold_uncertainty_score":0.2995869,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03742044249948087,"score_gpt":0.3314787121336442,"score_spread":0.2940582696341633,"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."}}