Proposed a novel method of contextual embedding mapping and revealed the tight relationship of isotropy, isometry and isomorphsim in contextual embedding spaces.
Proposed novel data augmentation approach for domain adaptation, which surpasses state-of-the-art performance in
Dialogue State Tracking and Event Extraction tasks.
Investigated a zero-shot approach for dependency parsing by building a multilingual concept-shared semantic space, which
achieves state-of-the-art performance.