{"id":"W2891881175","doi":"10.18653/v1/d18-1343","title":"Multi-Multi-View Learning: Multilingual and Multi-Representation Entity Typing","year":2018,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Computer science; Natural language processing; Embedding; Representation (politics); Artificial intelligence; Entity linking; Context (archaeology); German; Information retrieval; Linguistics; Knowledge base","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":[0.003603175,0.001849136,0.001751439,0.003844289,0.001124003,0.002740473,0.003866455,0.002211984,0.003914638],"category_scores_gemma":[0.01145776,0.0006694762,0.002128786,0.00503424,0.0007449675,0.006900279,0.004833982,0.003416672,0.002316138],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001210933,"about_ca_system_score_gemma":0.00128777,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008800288,"about_ca_topic_score_gemma":0.01598672,"domain_scores_codex":[0.9967245,0.0008799363,0.0002859458,0.001367221,0.0005248776,0.0002174641],"domain_scores_gemma":[0.9935847,0.002506557,0.0003047922,0.002632855,0.0006536734,0.0003174365],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001092066,0.001373406,0.02656425,0.001302529,0.0008547859,0.0008160432,0.0007246211,0.09036851,0.008615662,0.008710789,0.1227194,0.736858],"study_design_scores_gemma":[0.0001757823,0.0002531666,0.006008889,0.0001764131,0.0002683588,0.00095835,0.000582454,0.9006246,0.01386397,0.0357525,0.04123292,0.000102539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.117901,0.005130234,0.8142987,0.001424269,0.0004612871,0.0004641882,0.03433686,0.01987951,0.006103993],"genre_scores_gemma":[0.3958084,0.0009322164,0.4697609,0.0007823785,0.0002205257,0.0003618491,0.127912,0.0008432651,0.003378495],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008800288,"threshold_uncertainty_score":0.01905566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08456332633316738,"score_gpt":0.3519646892348669,"score_spread":0.2674013629016995,"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."}}