{"task":"Coreference Resolution","dataset":"GAP","metric_names":["Overall F1","Masculine F1 (M)","Feminine F1 (F)","Bias (F/M)","F1"],"rows":[{"id":52491,"task":"Coreference Resolution","parent_task":null,"dataset":"GAP","model_name":"Coref-MTL","metrics":{"Bias (F/M)":"0.99","Feminine F1 (F)":"92.45","Masculine F1 (M)":"92.65","Overall F1":"92.72"},"paper_url":null,"paper_title":null,"paper_date":null,"code_links":[],"metrics_order":"[\"Overall F1\", \"Masculine F1 (M)\", \"Feminine F1 (F)\", \"Bias (F/M)\", \"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52492,"task":"Coreference Resolution","parent_task":null,"dataset":"GAP","model_name":"ProBERT","metrics":{"Bias (F/M)":"0.97","Feminine F1 (F)":"91.1","Masculine F1 (M)":"94.0","Overall F1":"92.5"},"paper_url":"https://aclanthology.org/W19-3820","paper_title":"Gendered Ambiguous Pronouns Shared Task: Boosting Model Confidence by Evidence Pooling","paper_date":"2019-08-01","code_links":[{"title":"sattree/gap","url":"https://github.com/sattree/gap"}],"metrics_order":"[\"Overall F1\", \"Masculine F1 (M)\", \"Feminine F1 (F)\", \"Bias (F/M)\", \"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52493,"task":"Coreference Resolution","parent_task":null,"dataset":"GAP","model_name":"Maverick_incr","metrics":{"Overall F1":"91.2"},"paper_url":"https://arxiv.org/abs/2407.21489v1","paper_title":"Maverick: Efficient and Accurate Coreference Resolution Defying Recent Trends","paper_date":"2024-07-31","code_links":[{"title":"sapienzanlp/maverick-coref","url":"https://github.com/sapienzanlp/maverick-coref"}],"metrics_order":"[\"Overall F1\", \"Masculine F1 (M)\", \"Feminine F1 (F)\", \"Bias (F/M)\", \"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52494,"task":"Coreference Resolution","parent_task":null,"dataset":"GAP","model_name":"Full Ensemble","metrics":{"Bias (F/M)":"0.98","Feminine F1 (F)":"89.5","Masculine F1 (M)":"90.9","Overall F1":"90.2"},"paper_url":"https://arxiv.org/abs/1906.03695v1","paper_title":"Gendered Pronoun Resolution using BERT and an extractive question answering formulation","paper_date":"2019-06-09","code_links":[{"title":"rakeshchada/corefqa","url":"https://github.com/rakeshchada/corefqa"}],"metrics_order":"[\"Overall F1\", \"Masculine F1 (M)\", \"Feminine F1 (F)\", \"Bias (F/M)\", \"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]},{"id":52495,"task":"Coreference Resolution","parent_task":null,"dataset":"GAP","model_name":"PeTra","metrics":{"F1":"85.3"},"paper_url":"https://arxiv.org/abs/2005.02990v1","paper_title":"PeTra: A Sparsely Supervised Memory Model for People Tracking","paper_date":"2020-05-06","code_links":[{"title":"shtoshni92/petra","url":"https://github.com/shtoshni92/petra"}],"metrics_order":"[\"Overall F1\", \"Masculine F1 (M)\", \"Feminine F1 (F)\", \"Bias (F/M)\", \"F1\"]","area":"Natural Language Processing","uses_additional_data":0,"source":"archive","tags":[]}]}