Abstract: Recent Transformer-based models such as Transformer-XL and BERT have achieved huge success on various natural language processing tasks. However, contextualized embeddings at the output layer of these powerful models tend to degenerate and occupy an anisotropic cone in the vector space, which is called the representation degeneration problem. In this paper, we propose a novel spectrum control approach to address this degeneration problem. The core idea of our method is to directly guide the spectra training of the output embedding matrix with a slow-decaying singular value prior distribution through a reparameterization framework. We show that our proposed method encourages isotropy of the learned word representations while maintains the modeling power of these contextual neural models. We further provide a theoretical analysis and insight on the benefit of modeling singular value distribution. We demonstrate that our spectrum control method outperforms the state-of-the-art Transformer-XL modeling for language model, and various Transformer-based models for machine translation, on common benchmark datasets for these tasks.

Similar Papers

Lite Transformer with Long-Short Range Attention
Zhanghao Wu, Zhijian Liu, Ji Lin, Yujun Lin, Song Han,
Transformer-XH: Multi-Evidence Reasoning with eXtra Hop Attention
Chen Zhao, Chenyan Xiong, Corby Rosset, Xia Song, Paul Bennett, Saurabh Tiwary,
Are Transformers universal approximators of sequence-to-sequence functions?
Chulhee Yun, Srinadh Bhojanapalli, Ankit Singh Rawat, Sashank Reddi, Sanjiv Kumar,