Unified BERT for Few-shot Natural Language Understanding. (arXiv:2206.12094v2 [cs.CL] UPDATED)

Even as pre-trained language models share a semantic encoder, natural
language understanding suffers from a diversity of output schemas. In this
paper, we propose UBERT, a unified bidirectional language understanding model
based on BERT framework, which can universally model the training objects of
different NLU tasks through a biaffine network. Specifically, UBERT encodes
prior knowledge from various aspects, uniformly constructing learning
representations across multiple NLU tasks, which is conducive to enhancing the
ability to capture common semantic understanding. By using …

arxiv bert language natural natural language understanding