Ruo-Jing Dong

2 accepted papers

2025

A Lens into Interpretable Transformer Mistakes via Semantic Dependency

Ruo-Jing Dong, Yu Yao, Bo Han, Tongliang Liu

ICML 2025poster

Semantic Dependency refers to the relationship between words in a sentence where the meaning of one word depends on another, which is important for natural language understanding. In this paper, we investigate the role of semantic dependencies in answering questions for transformer models, which is…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

Can Label-Specific Features Help Partial-Label Learning?

Ruo-Jing Dong, Jun-Yi Hang, Tong Wei, Min-Ling Zhang

AAAI 2023technical

Partial label learning (PLL) aims to learn from inexact data annotations where each training example is associated with a coarse candidate label set. Due to its practicability, many PLL algorithms have been proposed in recent literature. Most prior PLL works attempt to identify the ground-truth labe…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗