EMNLP Findings2025
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 sub-embeddings, 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.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
Cited by top-tier papers1
Builds on8
- Revisiting Pre-Trained Models for Chinese Natural Language ProcessingYiming Cui, Wanxiang Che, Ting Liu, Bing Qin et al.EMNLP Findings 2020 · 866 citations
- Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain ActivitiesJingyuan Sun, Mingxiao Li, Zijiao Chen, Yunhao Zhang et al.NeurIPS 2023 · 57 citations
- Probing Word Syntactic Representations in the Brain by a Feature Elimination MethodXiaohan Zhang, Shaonan Wang, Nan Lin, Jiajun Zhang et al.AAAI 2022 · 26 citations
- Large Language Models Know What is Key Visual Entity: An LLM-assisted Multimodal Retrieval for VQAPu Jian, Donglei Yu, Jiajun ZhangEMNLP 2024 · 5 citations
- Interpreting and Exploiting Functional Specialization in Multi-Head Attention under Multi-task LearningChong Li, Shaonan Wang, Yunhao Zhang, Jiajun Zhang et al.EMNLP 2023 · 5 citations
Related papers
- Disentangling Superpositions: Interpretable Brain Encoding Model with Sparse Concept AtomsAlicia Zeng, Jack GallantNeurIPS 2025 · 5 citations
- Probing Brain Activation Patterns by Dissociating Semantics and Syntax in SentencesShaonan Wang, Jiajun Zhang, Nan Lin, Chengqing ZongAAAI 2020 · 23 citations
- The POLAR Framework: Polar Opposites Enable Interpretability of Pre-Trained Word EmbeddingsBinny Mathew, Sandipan Sikdar, Florian Lemmerich, Markus StrohmaierWWW 2020 · 40 citations
- SensePOLAR: Word sense aware interpretability for pre-trained contextual word embeddingsJan Engler, Sandipan Sikdar, Marlene Lutz, Markus StrohmaierEMNLP Findings 2022 · 3 citations
- Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual DisentanglementLinyang He, Tianjun Zhong, Richard J. Antonello, Gavin Mischler et al.NeurIPS 2025 · 6 citations
