Exploring Intra and Inter-language Consistency in Embeddings with ICA
This work addresses the need for interpretable and reliable semantic axes in word embeddings for NLP researchers, but it is incremental as it builds on prior research on ICA's potential.
The paper tackled the problem of verifying the consistency of semantic axes derived from Independent Component Analysis (ICA) in word embeddings, both within a single language and across multiple languages, by applying statistical methods to establish a robust framework for reliability and universality.
Word embeddings represent words as multidimensional real vectors, facilitating data analysis and processing, but are often challenging to interpret. Independent Component Analysis (ICA) creates clearer semantic axes by identifying independent key features. Previous research has shown ICA's potential to reveal universal semantic axes across languages. However, it lacked verification of the consistency of independent components within and across languages. We investigated the consistency of semantic axes in two ways: both within a single language and across multiple languages. We first probed into intra-language consistency, focusing on the reproducibility of axes by performing ICA multiple times and clustering the outcomes. Then, we statistically examined inter-language consistency by verifying those axes' correspondences using statistical tests. We newly applied statistical methods to establish a robust framework that ensures the reliability and universality of semantic axes.