{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027037,0.0001356352,0.0002069654,0.00006680428,0.00005775753,0.000282212,0.0004841235,0.00009746195,0.00000475311],"category_scores_gemma":[0.0000409549,0.0001091193,0.00002009684,0.0002231362,0.00007604435,0.0005533416,0.000390953,0.0002001148,0.00000846071],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004262557,"about_ca_system_score_gemma":0.0000401008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076153,"about_ca_topic_score_gemma":0.000001667712,"domain_scores_codex":[0.9989471,0.00003461275,0.0001981166,0.0003231157,0.0002653127,0.0002317855],"domain_scores_gemma":[0.999344,0.00005296182,0.00009158099,0.000241386,0.00007663921,0.0001934523],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003553777,0.0001748318,0.2568294,0.00008236797,0.00006052035,0.00005505111,0.006742539,0.000004944678,0.01539063,0.0211025,0.3766989,0.3228228],"study_design_scores_gemma":[0.003410454,0.0009193582,0.003810623,0.0004053699,0.0001456333,0.0002990249,0.0007252604,0.3635503,0.2463802,0.3249107,0.051274,0.004169087],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2306666,0.0009870772,0.7664373,0.0007227439,0.00007944108,0.00008323871,0.000001027682,0.0005681629,0.0004544204],"genre_scores_gemma":[0.571445,6.92031e-7,0.4279997,0.0003383562,0.00005655446,0.000001114079,0.000002058968,0.000005960485,0.0001506095],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.3635453,"threshold_uncertainty_score":0.4449756,"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."}}