Momose Oyama

6 papers · 2023–2025 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

EMNLP (4) ACL (1) COLING (1)

Top co-authors

Hidetoshi Shimodaira (6) Hiroaki Yamagiwa (5) Sho Yokoi (1) Ryo Kishino (1) Yusuke Takase (1)

Research topics

Machine Learning (6) Core Methods (6) Optimization & Theory (5) Artificial Intelligence (2) Deep Learning (2) Mathematics & Optimization (2) Core AI (2) Learning Types (2) Mathematics (2)

Keywords

independent component analysis (3) kullback-leibler divergence (2) word embedding (2) representation learning (2) semantic structure (1) model comparison (1) semantic similarity (1) semantic embedding (1) information gain (1) cosine similarity (1) interpretable representation (1) semantic component (1) contextualized embedding (1) multilingual embedding (1) autoregressive language model (1) embedding analysis (1) embedding norm (1) higher-order correlation (1) embedding interpretability (1) semantic axe (1)

Papers

Likelihood Variance as Text Importance for Resampling Texts to Map Language Models EMNLP 2025 Mapping 1,000+ Language Models via the Log-Likelihood Vector ACL 2025 Revisiting Cosine Similarity via Normalized ICA-transformed Embeddings COLING 2025 Understanding Higher-Order Correlations Among Semantic Components in Embeddings EMNLP 2024 Discovering Universal Geometry in Embeddings with ICA EMNLP 2023 Norm of Word Embedding Encodes Information Gain EMNLP 2023