Picture for Sho Yokoi

Sho Yokoi

Zipfian Whitening

Add code
Nov 01, 2024
Viaarxiv icon

Contrastive Learning-based Sentence Encoders Implicitly Weight Informative Words

Add code
Oct 24, 2023
Viaarxiv icon

Unbalanced Optimal Transport for Unbalanced Word Alignment

Add code
Jun 07, 2023
Viaarxiv icon

Transformer Language Models Handle Word Frequency in Prediction Head

Add code
May 29, 2023
Viaarxiv icon

Feed-Forward Blocks Control Contextualization in Masked Language Models

Add code
Feb 01, 2023
Viaarxiv icon

Norm of word embedding encodes information gain

Add code
Dec 19, 2022
Viaarxiv icon

Improving word mover's distance by leveraging self-attention matrix

Add code
Nov 11, 2022
Viaarxiv icon

Subspace-based Set Operations on a Pre-trained Word Embedding Space

Add code
Oct 24, 2022
Viaarxiv icon

Instance-Based Neural Dependency Parsing

Add code
Sep 28, 2021
Figure 1 for Instance-Based Neural Dependency Parsing
Figure 2 for Instance-Based Neural Dependency Parsing
Figure 3 for Instance-Based Neural Dependency Parsing
Figure 4 for Instance-Based Neural Dependency Parsing
Viaarxiv icon

Incorporating Residual and Normalization Layers into Analysis of Masked Language Models

Add code
Sep 15, 2021
Figure 1 for Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
Figure 2 for Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
Figure 3 for Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
Figure 4 for Incorporating Residual and Normalization Layers into Analysis of Masked Language Models
Viaarxiv icon