Ranking-Enhanced Unsupervised Sentence Representation Learning

TL;DR

This paper introduces RankEncoder, an unsupervised sentence encoder that improves semantic representations by incorporating relationships with nearest-neighbor sentences, leading to better performance on semantic benchmarks.

Contribution

The paper proposes a novel ranking-based approach, RankEncoder, which leverages external corpus relationships to enhance unsupervised sentence embeddings.

Findings

Achieves 80.07% Spearman's correlation, surpassing previous state-of-the-art.

Universally applicable to existing unsupervised methods.

Effective in predicting similarity scores of similar sentence pairs.

Abstract

Unsupervised sentence representation learning has progressed through contrastive learning and data augmentation methods such as dropout masking. Despite this progress, sentence encoders are still limited to using only an input sentence when predicting its semantic vector. In this work, we show that the semantic meaning of a sentence is also determined by nearest-neighbor sentences that are similar to the input sentence. Based on this finding, we propose a novel unsupervised sentence encoder, RankEncoder. RankEncoder predicts the semantic vector of an input sentence by leveraging its relationship with other sentences in an external corpus, as well as the input sentence itself. We evaluate RankEncoder on semantic textual benchmark datasets. From the experimental results, we verify that 1) RankEncoder achieves 80.07% Spearman's correlation, a 1.1% absolute improvement compared to the previous state-of-the-art performance, 2) RankEncoder is universally applicable to existing unsupervised sentence embedding methods, and 3) RankEncoder is specifically effective for predicting the similarity scores of similar sentence pairs.