Cross-domain NER is a challenging yet practical problem . We investigate a multi-cell compositional LSTM structure for multi-task learning . Theoretically, the resulting distinct feature distributions for each entity type make it more powerful for cross-domain transfer . Empirically, experiments on four few-shot and zero-shot datasets show our method significantly outperforms a series of multi- task learning methods and achieves the best results. Empirally, experiments show that the method significantly outshines multi-Task learning methods .

Links: PDF - Abstract

Code :

None

Keywords : multi - domain - learning - task - shot -

Leave a Reply

Your email address will not be published. Required fields are marked *

error

Enjoy this blog? Please spread the word :)