Whitening Sentence Representations for Better Semantics and Faster Retrieval
arXiv:2103.15316
Abstract
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.
The source code of this paper is available at https://github.com/bojone/BERT-whitening
References in corpus (2)
Cited by in corpus (8)
- A Review-aware Graph Contrastive Learning Framework for Recommendation
- Improving Speech Translation by Cross-Modal Multi-Grained Contrastive Learning
- Leveraging Advantages of Interactive and Non-Interactive Models for Vector-Based Cross-Lingual Information Retrieval
- Emotions are Subtle: Learning Sentiment Based Text Representations Using Contrastive Learning
- DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings
- Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast
- Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
- WhiteningBERT: An Easy Unsupervised Sentence Embedding Approach