shimo-lab / Universal-Geometry-with-ICA

Discovering Universal Geometry in Embeddings with ICA
https://aclanthology.org/2023.emnlp-main.283/
15 stars 0 forks source link
cross-lingual embeddings emnlp emnlp2023 ica independent-component-analysis interpretability isotropy pca principal-component-analysis whitening

Universal-Geometry-with-ICA

Discovering Universal Geometry in Embeddings with ICA
Hiroaki Yamagiwa*, Momose Oyama*, Hidetoshi Shimodaira
EMNLP 2023

English word embeddings

Heatmap of ICA-transformed word embeddings

heatmap

Cross-lingual embeddings

Heatmaps of ICA-transformed word embeddings

cross-lingual heatmap

Spiky shape of embedding distributions

ica shape

Scatter plots of ICA-transformed word embeddings

English Spanish
ica en ica es
Russian Arabic Hindi Chinese Japanese
ica ru ica ar ica hi ica zh ica ja

Code and Data

Citation

If you find our code or data useful in your research, please cite our paper:

@inproceedings{DBLP:conf/emnlp/YamagiwaOS23,
  author       = {Hiroaki Yamagiwa and
                  Momose Oyama and
                  Hidetoshi Shimodaira},
  editor       = {Houda Bouamor and
                  Juan Pino and
                  Kalika Bali},
  title        = {Discovering Universal Geometry in Embeddings with {ICA}},
  booktitle    = {Proceedings of the 2023 Conference on Empirical Methods in Natural
                  Language Processing, {EMNLP} 2023, Singapore, December 6-10, 2023},
  pages        = {4647--4675},
  publisher    = {Association for Computational Linguistics},
  year         = {2023},
  url          = {https://aclanthology.org/2023.emnlp-main.283},
  timestamp    = {Wed, 13 Dec 2023 17:20:20 +0100},
  biburl       = {https://dblp.org/rec/conf/emnlp/YamagiwaOS23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}