Discovering Universal Geometry in Embeddings with ICA

Hiroaki Yamagiwa, Momose Oyama, Hidetoshi Shimodaira


Abstract
This study utilizes Independent Component Analysis (ICA) to unveil a consistent semantic structure within embeddings of words or images. Our approach extracts independent semantic components from the embeddings of a pre-trained model by leveraging anisotropic information that remains after the whitening process in Principal Component Analysis (PCA). We demonstrate that each embedding can be expressed as a composition of a few intrinsic interpretable axes and that these semantic axes remain consistent across different languages, algorithms, and modalities. The discovery of a universal semantic structure in the geometric patterns of embeddings enhances our understanding of the representations in embeddings.
Anthology ID:
2023.emnlp-main.283
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4647–4675
Language:
URL:
https://aclanthology.org/2023.emnlp-main.283
DOI:
10.18653/v1/2023.emnlp-main.283
Bibkey:
Cite (ACL):
Hiroaki Yamagiwa, Momose Oyama, and Hidetoshi Shimodaira. 2023. Discovering Universal Geometry in Embeddings with ICA. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 4647–4675, Singapore. Association for Computational Linguistics.
Cite (Informal):
Discovering Universal Geometry in Embeddings with ICA (Yamagiwa et al., EMNLP 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2023.emnlp-main.283.pdf
Video:
 https://preview.aclanthology.org/nschneid-patch-5/2023.emnlp-main.283.mp4