NLP

Cross-Lingual Contextual Embedding Space Mapping

Proposed a novel method of contextual embedding mapping and revealed the tight relationship of isotropy, isometry and isomorphsim in contextual embedding spaces.

Gradual Fine-Tuning for Low-Resource Domain Adaptation

Proposed novel data augmentation approach for domain adaptation, which surpasses state-of-the-art performance in Dialogue State Tracking and Event Extraction tasks.

Zero-Shot Cross-Lingual Dependency Parsing

Investigated a zero-shot approach for dependency parsing by building a multilingual concept-shared semantic space, which achieves state-of-the-art performance.