1 citations · 3 across the 14 of their papers we have counts for
Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
Assessing the quality and coherence of word embeddings after SCM-based intersectional bias mitigation
Eren Kocadag, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag
Static word embeddings often absorb social biases from the text they learn from, and those biases can quietly shape downstream systems. Prior work that uses the Stereotype Content…
cs.AI2026
Cross-Language Speaker Attribute Prediction Using MIL and RL
Sunny Shu, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag
We study multilingual speaker attribute prediction under linguistic variation, domain mismatch, and data imbalance across languages. We propose RLMIL-DAT, a multilingual extension…