LUKE
University of WashingtonNational Institute of InformaticsQuestion answeringRelation extractionNamed entity recognition (NER)Open weights
Developed by University of Washington,National Institute of Informatics in 2020, LUKE is a question answering model with 483000000.0 parameters with openly available weights.
About LUKE
Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the bidirectional transformer. The proposed model treats words and
Details
- Provider
- University of Washington,National Institute of Informatics
- Task
- Question answering,Relation extraction,Named entity recognition (NER)
- Parameters
- 483000000.0
- Released
- 2020-10-02
- Open weights
- Yes