{"id":"W2251786640","doi":"10.3115/v1/p15-2108","title":"Lexical Comparison Between Wikipedia and Twitter Corpora by Using Word Embeddings","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Computational linguistics; Zhàng; Artificial intelligence; Volume (thermodynamics); Word (group theory); Joint (building); Association (psychology); Linguistics; History; Engineering; China; Psychology; Philosophy","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":[0.001679275,0.0006594348,0.000641546,0.01207878,0.001258333,0.00234179,0.0008195454,0.000631495,0.005564527],"category_scores_gemma":[0.0132702,0.0003850317,0.0006965133,0.0102727,0.0004293141,0.005464577,0.002954839,0.000735158,0.005416666],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000548081,"about_ca_system_score_gemma":0.001065074,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003448709,"about_ca_topic_score_gemma":0.0110327,"domain_scores_codex":[0.9976014,0.0006393876,0.0005340501,0.0004985869,0.0005715789,0.0001549156],"domain_scores_gemma":[0.9932243,0.002187618,0.0005573116,0.001072996,0.002652019,0.0003056954],"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":[0.002131307,0.0008161738,0.05461894,0.005539371,0.001269022,0.001958625,0.004175334,0.004094017,0.05703493,0.02075142,0.29115,0.5564607],"study_design_scores_gemma":[0.0005470785,0.0007899489,0.154467,0.001555965,0.001188219,0.002884974,0.02272541,0.09881511,0.05527122,0.04178731,0.6194624,0.0005054019],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5763645,0.007199904,0.1154811,0.002159081,0.004516806,0.0008266201,0.2386072,0.01133872,0.04350615],"genre_scores_gemma":[0.4631371,0.001735831,0.1145094,0.0003162543,0.0004543479,0.00119214,0.4081096,0.001987094,0.008558184],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01207878,"threshold_uncertainty_score":0.01861525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07377720145457405,"score_gpt":0.3422680295978668,"score_spread":0.2684908281432927,"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."}}