The MT-DNN architecture proposed by Choi and Ko (2023) utilizes multi-task learning by combining Entity Description Prediction (EDP) and Entity Type Prediction (ITP) tasks, sharing a pre-trained language model and network layers for joint training.

Authors

• Person: Not available Organization: Frontiers
  Practices, opportunities and challenges in the fusion of knowledge ...

Sources

• Practices, opportunities and challenges in the fusion of knowledge ... www.frontiersin.org Frontiers via serper

Referenced by nodes (1)

• multi-task learning concept