Jun Ma

A deep learning framework for translation quality estimation using dual stream cross lingual attention and gated mixture of experts prediction

DL-TQE is proposed, a deep learning architecture comprising two components: a Dual-Stream Cross-Lingual Attention Network (DSCAN) with parallel Transformer encoders connected by explicit cross-lingual attention bridges at multiple layers, and a Gated Mixture-of-Experts Quality Predictor that routes quality-relevant fea...