Disentangling Linguistic Features with Dimension-Wise Analysis of Vector Embeddings

ACL ARR 2025 February Submission5033 Authors

Abstract: Understanding the inner workings of neural embeddings, particularly in models such as BERT, remains a challenge because of their high-dimensional and opaque nature. This paper proposes a framework for uncovering the specific dimensions of vector embeddings that encode distinct linguistic properties (LPs). We introduce the Linguistically Distinct Sentence Pairs (LDSP-10) dataset, which isolates ten key linguistic features such as synonymy, negation, tense, and quantity. Using this dataset, we analyze BERT embeddings with various statistical methods, including the Wilcoxon signed-rank test, mutual information, and recursive feature elimination, to identify the most influential dimensions for each LP. We introduce a new metric, the Embedding Dimension Importance (EDI) score, which quantifies the relevance of each embedding dimension to a LP. Our findings show that certain properties, such as negation and polarity, are robustly encoded in specific dimensions, while others, like synonymy, exhibit more complex patterns. This study provides insights into the interpretability of embeddings, which can guide the development of more transparent and optimized language models, with implications for model bias mitigation and the responsible deployment of AI systems.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: interpretability, embeddings, BERT, GPT, LLM, natural language processing, linguistics, disentanglement

Contribution Types: Model analysis & interpretability, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 5033