Whitening Sentence Representations for Better Semantics and Faster Retrieval
This work addresses a critical bottleneck in sentence representation for natural language processing, offering an incremental improvement over existing methods.
The paper tackles the anisotropy problem in BERT-based sentence representations by applying a whitening operation, which enhances isotropy and reduces dimensionality, leading to competitive performance, reduced storage cost, and faster retrieval speeds.
Pre-training models such as BERT have achieved great success in many natural language processing tasks. However, how to obtain better sentence representation through these pre-training models is still worthy to exploit. Previous work has shown that the anisotropy problem is an critical bottleneck for BERT-based sentence representation which hinders the model to fully utilize the underlying semantic features. Therefore, some attempts of boosting the isotropy of sentence distribution, such as flow-based model, have been applied to sentence representations and achieved some improvement. In this paper, we find that the whitening operation in traditional machine learning can similarly enhance the isotropy of sentence representations and achieve competitive results. Furthermore, the whitening technique is also capable of reducing the dimensionality of the sentence representation. Our experimental results show that it can not only achieve promising performance but also significantly reduce the storage cost and accelerate the model retrieval speed.