Xiuwen Liu

Latest

• Too Much in Common: Shifting of Embeddings in Transformer Language Models and its Implications
• Effects of Architecture and Training on Embedding Geometry and Feature Discriminability in BERT
• Biomedical word sense disambiguation with bidirectional long short-term memory and attention-based neural networks
• An Analysis on the Learning Rules of the Skip-Gram Model
• Layered Multistep Bidirectional Long Short-Term Memory Networks for Biomedical Word Sense Disambiguation