HUBERT Untangles BERT to Improve Transfer across NLP Tasks

ICLR 2020 Mehrad MoradshahiHamid PalangiMonica S. LamPaul SmolenskyJianfeng Gao

We introduce HUBERT which combines the structured-representational power of Tensor-Product Representations (TPRs) and BERT, a pre-trained bidirectional Transformer language model. We show that there is shared structure between different NLP datasets that HUBERT, but not BERT, is able to learn and leverage... (read more)

PDF Abstract


No code implementations yet. Submit your code now

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper