[go: up one dir, main page]

Follow
Momose Oyama
Momose Oyama
Verified email at sys.i.kyoto-u.ac.jp - Homepage
Title
Cited by
Cited by
Year
Discovering Universal Geometry in Embeddings with ICA
H Yamagiwa*, M Oyama*, H Shimodaira
Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2023
222023
Norm of Word Embedding Encodes Information Gain
M Oyama, S Yokoi, H Shimodaira
Proceedings of the 2023 Conference on Empirical Methods in Natural Language …, 2022
202022
Revisiting cosine similarity via normalized ica-transformed embeddings
H Yamagiwa, M Oyama, H Shimodaira
Proceedings of the 31st International Conference on Computational …, 2025
92025
Predicting drug–gene relations via analogy tasks with word embeddings
H Yamagiwa, R Hashimoto, K Arakane, K Murakami, S Soeda, M Oyama, ...
Scientific Reports 15 (1), 17240, 2025
42025
Mapping 1,000+ Language Models via the Log-Likelihood Vector
M Oyama, H Yamagiwa, Y Takase, H Shimodaira
arXiv preprint arXiv:2502.16173, 2025
22025
Understanding Higher-Order Correlations Among Semantic Components in Embeddings
M Oyama, H Yamagiwa, H Shimodaira
EMNLP 2024, 2024
22024
Likelihood Variance as Text Importance for Resampling Texts to Map Language Models
M Oyama, R Kishino, H Yamagiwa, H Shimodaira
arXiv preprint arXiv:2505.15428, 2025
12025
Revealing Language Model Trajectories via Kullback-Leibler Divergence
R Kishino, Y Takase, M Oyama, H Yamagiwa, H Shimodaira
arXiv preprint arXiv:2505.15353, 2025
2025
Analogy Tasks in BioConceptVec using Biological Pathways
H Yamagiwa, R Hashimoto, K Arakane, K Murakami, M Oyama, ...
IEICE Technical Report; IEICE Tech. Rep. 123 (91), 113-120, 2023
2023
A Mechanism of Implicit Regularization in Deep Learning
M Kubo, G Sugiura, K Shinzato, M Oyama
The system can't perform the operation now. Try again later.
Articles 1–10