@inproceedings{zhang-etal-2025-discovering,
    title = "Discovering Semantic Subdimensions through Disentangled Conceptual Representations",
    author = "Zhang, Yunhao  and
      Wang, Shaonan  and
      Lin, Nan  and
      Dong, Xinyi  and
      Li, Chong  and
      Zong, Chengqing",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.325/",
    doi = "10.18653/v1/2025.findings-emnlp.325",
    pages = "6127--6144",
    ISBN = "979-8-89176-335-7",
    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 $\textbf{D}$isentangled $\textbf{C}$ontinuous $\textbf{S}$emantic $\textbf{R}$epresentation $\textbf{M}$odel ($\textbf{DCSRM}$) 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."
}