@inproceedings{ponwitayarat-etal-2024-space,
title = "Space Decomposition for Sentence Embedding",
author = "Ponwitayarat, Wuttikorn and
Limkonchotiwat, Peerat and
Chuangsuwanich, Ekapol and
Nutanong, Sarana",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.668/",
doi = "10.18653/v1/2024.findings-acl.668",
pages = "11227--11239",
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."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ponwitayarat-etal-2024-space">
<titleInfo>
<title>Space Decomposition for Sentence Embedding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wuttikorn</namePart>
<namePart type="family">Ponwitayarat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peerat</namePart>
<namePart type="family">Limkonchotiwat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekapol</namePart>
<namePart type="family">Chuangsuwanich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarana</namePart>
<namePart type="family">Nutanong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">ponwitayarat-etal-2024-space</identifier>
<identifier type="doi">10.18653/v1/2024.findings-acl.668</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.668/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>11227</start>
<end>11239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Space Decomposition for Sentence Embedding
%A Ponwitayarat, Wuttikorn
%A Limkonchotiwat, Peerat
%A Chuangsuwanich, Ekapol
%A Nutanong, Sarana
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics: ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F ponwitayarat-etal-2024-space
%X 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.
%R 10.18653/v1/2024.findings-acl.668
%U https://aclanthology.org/2024.findings-acl.668/
%U https://doi.org/10.18653/v1/2024.findings-acl.668
%P 11227-11239
Markdown (Informal)
[Space Decomposition for Sentence Embedding](https://aclanthology.org/2024.findings-acl.668/) (Ponwitayarat et al., Findings 2024)
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.