Discovering Semantic Subdimensions through Disentangled Conceptual Representations

Yunhao Zhang, Shaonan Wang, Nan Lin, Xinyi Dong, Chong Li, Chengqing Zong


Abstract
Understanding the core dimensions of conceptual semantics is fundamental to uncovering how meaning is organized in language and the brain. Existing approaches often rely on predefined semantic dimensions that offer only broad representations, overlooking finer conceptual distinctions. This paper proposes a novel framework to investigate the subdimensions underlying coarse-grained semantic dimensions. Specifically, we introduce a Disentangled Continuous Semantic Representation Model (DCSRM) that decomposes word embeddings from large language models into multiple sub-embeddings, each encoding specific semantic information. Using these subembeddings, we identify a set of interpretable semantic subdimensions. To assess their neural plausibility, we apply voxel-wise encoding models to map these subdimensions to brain activation. Our work offers more fine-grained interpretable semantic subdimensions of conceptual meaning. Further analyses reveal that semantic dimensions are structured according to distinct principles, with polarity emerging as a key factor driving their decomposition into subdimensions. The neural correlates of the identified subdimensions support their cognitive and neuroscientific plausibility.
Anthology ID:
2025.findings-emnlp.325
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2025
Month:
November
Year:
2025
Address:
Suzhou, China
Editors:
Christos Christodoulopoulos, Tanmoy Chakraborty, Carolyn Rose, Violet Peng
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6127–6144
Language:
URL:
https://aclanthology.org/2025.findings-emnlp.325/
DOI:
Bibkey:
Cite (ACL):
Yunhao Zhang, Shaonan Wang, Nan Lin, Xinyi Dong, Chong Li, and Chengqing Zong. 2025. Discovering Semantic Subdimensions through Disentangled Conceptual Representations. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 6127–6144, Suzhou, China. Association for Computational Linguistics.
Cite (Informal):
Discovering Semantic Subdimensions through Disentangled Conceptual Representations (Zhang et al., Findings 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.findings-emnlp.325.pdf
Checklist:
 2025.findings-emnlp.325.checklist.pdf