{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001075569,0.0006038567,0.0004031326,0.001601961,0.0004222373,0.001220022,0.0004661859,0.0005512749,0.003249325],"category_scores_gemma":[0.004425005,0.0005578109,0.0005832593,0.0006481379,0.0004697897,0.003107894,0.001085531,0.00132979,0.002637409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006053099,"about_ca_system_score_gemma":0.0008051221,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001279011,"about_ca_topic_score_gemma":0.001638681,"domain_scores_codex":[0.9993356,0.000163025,0.00006942808,0.0002813441,0.00008590304,0.00006463298],"domain_scores_gemma":[0.9978253,0.000924993,0.0002573266,0.0002459975,0.000640376,0.0001060792],"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":[0.0009598696,0.0003121309,0.09591027,0.0008799175,0.0001263591,0.001935286,0.005184554,0.007465072,0.2991124,0.02092781,0.01764772,0.5495386],"study_design_scores_gemma":[0.0001181297,0.0008393952,0.201665,0.000356746,0.0003317608,0.006289718,0.008326554,0.5316431,0.1380048,0.03604274,0.07611299,0.0002690686],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8009186,0.0006407504,0.1811216,0.0004942706,0.0001568391,0.0001132827,0.002850934,0.002859955,0.01084365],"genre_scores_gemma":[0.917729,0.0003856149,0.07061923,0.0001354451,0.00006157615,0.0001235727,0.006808242,0.0005713076,0.003566073],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.003249325,"threshold_uncertainty_score":0.01087004,"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."}}