Space Decomposition for Sentence Embedding

Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, Sarana Nutanong


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.
Anthology ID:
2024.findings-acl.668
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11227–11239
Language:
URL:
https://aclanthology.org/2024.findings-acl.668
DOI:
10.18653/v1/2024.findings-acl.668
Bibkey:
Cite (ACL):
Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Ekapol Chuangsuwanich, and Sarana Nutanong. 2024. Space Decomposition for Sentence Embedding. In Findings of the Association for Computational Linguistics: ACL 2024, pages 11227–11239, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Space Decomposition for Sentence Embedding (Ponwitayarat et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2024.findings-acl.668.pdf