Space Decomposition for Sentence Embedding
Abstract
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 lower-range samples. This necessitates a new approach to treating the upper-range and lower-range 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.
Cite
@article{arxiv.2406.03125,
title = {Space Decomposition for Sentence Embedding},
author = {Wuttikorn Ponwitayarat and Peerat Limkonchotiwat and Ekapol Chuangsuwanich and Sarana Nutanong},
journal= {arXiv preprint arXiv:2406.03125},
year = {2024}
}
Comments
ACL Finding 2024. The code and pre-trained models are available at https://github.com/KornWtp/MixSP