📝 Highlighted Research

DRr-Net: Dynamic Re-Read Network for Sentence Semantic Matching

Kun Zhang, Guangyi Lv, Linyuan Wang, Le Wu, Enhong Chen, Fangzhao Wu, and Xing Xie

• This work draws inspiration from cognitive psychology and designs dynamic attention mechanism (DRr-Net) to realize the focusing and dynamic adjustment of attention, improving the quality of generated sentence representations.
• This work is also extend to IEEE TNNLS2022.

Description-Enhanced Label Embedding Contrastive Learning for Text Classification

Kun Zhang, Le Wu, Guangyi Lv, Enhong Chen, Shulan Ruan, Jing Liu, Zhiqiang Zhang, Jun Zhou, Meng Wang

• The previous work R$^2$-Net has been accepted by AAAI 2021
• This work proposed a novel self-supervised learning framework to make full use of label information to achieve high-quality sentence representation generation and relation inference.

Label-aware Debiased Causal Reasoning for Natural Language Inference

Kun Zhang*, Dacao Zhang, Le Wu, Richang Hong, Ye Zhao, Meng Wang, AI Open.

• This work proposes that label information can be used to guide the spurious correlation identification. Thus, it treats label information as one variable in causal graph and utilizes counterfactual inference to remove the spurious correlations introduced by human annotations.Finally, it realize debiased and robust natural language inference.
• We also extend this work into multi-modal scenarios and public one high-quality paper in Journal of Computer Research and Development.