Space Decomposition for Sentence Embedding
Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, Sarana Y. Nutanong · 2024
Determining sentence pair similarity is crucial for various NLP tasks.A common technique to address this is typically evaluated on a continuous semantic textual similarity scale from 0 to 5.However, based on a linguistic observation in STS annotation guidelines, we found that the score in the range [4,5] indicates an upper-range sample, while the rest are lowerrange samples.This necessitates a new approach to treating the upper-range and lowerrange classes separately.In this paper, we introduce a novel embedding space decomposition method called MixSP utilizing a Mixture of Specialized Projectors, designed to distinguish and rank upper-range and lower-range samples accurately.The experimental results demonstrate that MixSP decreased the overlap representation between upper-range and lower-range classes significantly while outperforming competitors on STS and zero-shot benchmarks. 1