A Sentence is Worth 128 Pseudo Tokens: A Semantic-Aware Contrastive Learning Framework for Sentence Embeddings
This addresses a key limitation in unsupervised sentence embedding for NLP applications, offering an incremental improvement over methods like SimCSE.
The paper tackles the problem of existing contrastive learning methods for sentence embeddings being affected by superficial features like sentence length and syntax, proposing a semantics-aware framework called PT-BERT that maps sentences into fixed-length pseudo tokens to improve learning; it outperforms state-of-the-art baselines on six STS tasks.
Contrastive learning has shown great potential in unsupervised sentence embedding tasks, e.g., SimCSE. However, We find that these existing solutions are heavily affected by superficial features like the length of sentences or syntactic structures. In this paper, we propose a semantics-aware contrastive learning framework for sentence embeddings, termed Pseudo-Token BERT (PT-BERT), which is able to exploit the pseudo-token space (i.e., latent semantic space) representation of a sentence while eliminating the impact of superficial features such as sentence length and syntax. Specifically, we introduce an additional pseudo token embedding layer independent of the BERT encoder to map each sentence into a sequence of pseudo tokens in a fixed length. Leveraging these pseudo sequences, we are able to construct same-length positive and negative pairs based on the attention mechanism to perform contrastive learning. In addition, we utilize both the gradient-updating and momentum-updating encoders to encode instances while dynamically maintaining an additional queue to store the representation of sentence embeddings, enhancing the encoder's learning performance for negative examples. Experiments show that our model outperforms the state-of-the-art baselines on six standard semantic textual similarity (STS) tasks. Furthermore, experiments on alignments and uniformity losses, as well as hard examples with different sentence lengths and syntax, consistently verify the effectiveness of our method.