Yi Zhou

Publication Activity (10 Years)

Years Active: 2021-2024
Publications (10 Years): 14

Top Topics

Cosine Similarity

Top Venues

Publications

Yi Zhou, Danushka Bollegala, José Camacho-Collados
Evaluating Short-Term Temporal Fluctuations of Social Biases in Social Media Data and Masked Language Models. CoRR (2024)
Haochen Luo, Yi Zhou, Danushka Bollegala
Together We Make Sense-Learning Meta-Sense Embeddings. ACL (Findings) (2023)
Saeth Wannasuphoprasit, Yi Zhou, Danushka Bollegala
Solving Cosine Similarity Underestimation between High Frequency Words by L2 Norm Discounting. CoRR (2023)
Yi Zhou, José Camacho-Collados, Danushka Bollegala
A Predictive Factor Analysis of Social Biases and Task-Performance in Pretrained Masked Language Models. CoRR (2023)
Saeth Wannasuphoprasit, Yi Zhou, Danushka Bollegala
Solving Cosine Similarity Underestimation between High Frequency Words by \ell₂ Norm Discounting. ACL (Findings) (2023)
Xiaohang Tang, Yi Zhou, Danushka Bollegala
Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation. ACL (1) (2023)
Haochen Luo, Yi Zhou, Danushka Bollegala
Together We Make Sense - Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddings. CoRR (2023)
Xiaohang Tang, Yi Zhou, Taichi Aida, Procheta Sen, Danushka Bollegala
Can Word Sense Distribution Detect Semantic Changes of Words? CoRR (2023)
Yi Zhou, Masahiro Kaneko, Danushka Bollegala
Sense Embeddings are also Biased-Evaluating Social Biases in Static and Contextualised Sense Embeddings. CoRR (2022)
Xiaohang Tang, Yi Zhou, Danushka Bollegala
Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation. CoRR (2022)
Yi Zhou, Danushka Bollegala
norm of Sense Embeddings. CoRR (2022)
Yi Zhou, Danushka Bollegala
On the Curious Case of l2 norm of Sense Embeddings. EMNLP (Findings) (2022)
Yi Zhou, Masahiro Kaneko, Danushka Bollegala
Sense Embeddings are also Biased - Evaluating Social Biases in Static and Contextualised Sense Embeddings. ACL (1) (2022)
Danushka Bollegala, Yi Zhou
Learning Sense-Specific Static Embeddings using Contextualised Word Embeddings as a Proxy. PACLIC (2021)