{"id":"W3169035567","doi":"10.1145/3447548.3467196","title":"Reinforced Iterative Knowledge Distillation for Cross-Lingual Named Entity Recognition","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Named-entity recognition; Leverage (statistics); Artificial intelligence; Natural language processing; Ranking (information retrieval); Entity linking; Component (thermodynamics); Benchmark (surveying); Labeled data; Machine learning; Information retrieval; 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":[0.0001812715,0.00007628861,0.00009189779,0.00003510236,0.0001371016,0.0002969342,0.0001511258,0.00005138878,0.0000544856],"category_scores_gemma":[0.0002881454,0.0000750316,0.00006039828,0.0001442662,0.00001458815,0.0005223109,0.0001053974,0.00005396397,0.00004309292],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004736521,"about_ca_system_score_gemma":0.0001029423,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007168483,"about_ca_topic_score_gemma":0.00003081201,"domain_scores_codex":[0.9992116,0.00003134368,0.0002053752,0.0003045941,0.00009741869,0.0001496839],"domain_scores_gemma":[0.999063,0.0001206481,0.00005294563,0.0002480939,0.0004702128,0.00004506108],"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":[0.00004225531,0.000101543,0.001225419,0.0001773536,0.00006927376,0.00001604578,0.01026955,0.002817263,0.01328197,0.3029485,0.0007044246,0.6683464],"study_design_scores_gemma":[0.0005108744,0.00002835025,0.0003947523,0.00002200297,0.000003742317,0.000006312593,0.00003593865,0.9185221,0.06937601,0.009034073,0.001908004,0.0001578633],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1258498,0.00002971564,0.8659784,0.0001174535,0.0005223059,0.0001414803,0.000005418598,0.0001140339,0.007241368],"genre_scores_gemma":[0.8609893,0.000002637247,0.1308417,0.0001024808,0.0001735411,0.00002349644,0.00005102814,0.000004886599,0.007810896],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9157048,"threshold_uncertainty_score":0.30597,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0514276670580911,"score_gpt":0.3317543473296186,"score_spread":0.2803266802715275,"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."}}