Sho Yokoi
26 papers · 2017–2026 · 9 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 ↓+7 more ↓ Show less ↑
🗺️ Taxonomy Completionist (49) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Gold 🐣 Hot Topic Early Bird
🤝
Dynamic Duo
(17)
⚡
Prolific Year · Productive
🔥
Unstoppable · Bronze
❓
The Questioner
💎
Century Club · Bronze
📈
Trend Setter
🗃️
Keyword Collector
(131)
Top co-authors
Research topics
Machine Learning
(22)
Natural Language Processing
(18)
Core Methods
(16)
Artificial Intelligence
(12)
Core AI
(11)
Resources & Methods
(8)
Deep Learning
(7)
Optimization & Theory
(7)
Understanding
(6)
Generation
(5)
Mathematics & Optimization
(4)
Applications
(4)
Architectures
(4)
Learning Types
(4)
Optimization
(4)
Keywords
word embedding
(8)
representation learning
(4)
optimal transport
(4)
semantic similarity
(3)
word alignment
(3)
attention mechanism
(2)
embedding learning
(2)
contextualized embedding
(2)
hilbert-schmidt independence criterion
(2)
information gain
(2)
unsupervised learning
(2)
text representation
(2)
knowledge distillation
(1)
contrastive learning
(1)
model compression
(1)
similarity learning
(1)
text generation
(1)
hierarchical classification
(1)
transformer architecture
(1)
named entity recognition
(1)
Papers
Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings
ACL 2026
On Entity Identification in Language Models
ACL 2025
Quantifying Lexical Semantic Shift via Unbalanced Optimal Transport
ACL 2025
SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
ICLR 2025
TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
ICLR 2025
Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps
ICLR 2024
Subspace Representations for Soft Set Operations and Sentence Similarities
NAACL 2024
Zipfian Whitening
NeurIPS 2024
Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words
EMNLP 2023
Improving word mover’s distance by leveraging self-attention matrix
EMNLP 2023
Norm of Word Embedding Encodes Information Gain
EMNLP 2023
Transformer Language Models Handle Word Frequency in Prediction Head
ACL 2023
Unbalanced Optimal Transport for Unbalanced Word Alignment
ACL 2023
Why is sentence similarity benchmark not predictive of application-oriented task performance?
AACL 2022
Computationally Efficient Wasserstein Loss for Structured Labels
EACL 2021
Evaluation of Similarity-based Explanations
ICLR 2021
Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
EMNLP 2021
Attention is Not Only a Weight: Analyzing Transformers with Vector Norms
EMNLP 2020
Efficient Estimation of Influence of a Training Instance
EMNLP 2020
Filtering Noisy Dialogue Corpora by Connectivity and Content Relatedness
EMNLP 2020
Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
ACL 2020
Modeling Event Salience in Narratives via Barthes’ Cardinal Functions
COLING 2020
Word Rotator’s Distance
EMNLP 2020
Pointwise HSIC: A Linear-Time Kernelized Co-occurrence Norm for Sparse Linguistic Expressions
EMNLP 2018
Unsupervised Learning of Style-sensitive Word Vectors
ACL 2018
Learning Co-Substructures by Kernel Dependence Maximization
IJCAI 2017