{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003640336,0.0001575434,0.0001717656,0.00009648965,0.0002752012,0.0002103198,0.0004150869,0.00008149893,0.00003770404],"category_scores_gemma":[0.0002343968,0.0001464906,0.00004749782,0.0001997126,0.00008946631,0.0005704992,0.0004472275,0.0001919575,0.0001357923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003004225,"about_ca_system_score_gemma":0.00003863888,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004306138,"about_ca_topic_score_gemma":0.0003215257,"domain_scores_codex":[0.9985203,0.0001165471,0.0002819361,0.0006150724,0.0001640044,0.0003021474],"domain_scores_gemma":[0.9991212,0.00007035489,0.0000944804,0.0004200302,0.0001747977,0.0001190967],"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":[0.00001243737,0.0004155027,0.09347612,0.00009229883,0.00006754,0.00001730174,0.01319472,0.001264558,0.02370838,0.00205823,0.00007141114,0.8656215],"study_design_scores_gemma":[0.0009023186,0.00002985331,0.01217069,0.0000249459,0.00000551109,0.000008712721,0.0001488457,0.9805927,0.005002005,0.00002429711,0.000903973,0.0001861882],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1859965,0.0001617375,0.8127279,0.0001234134,0.0003765829,0.0001720849,2.612879e-7,0.000278484,0.0001630166],"genre_scores_gemma":[0.5450189,0.00002305159,0.4533717,0.0001116217,0.00007606955,0.000004835727,0.000001004527,0.000007571514,0.001385277],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9793281,"threshold_uncertainty_score":0.5973714,"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."}}