Junliang He

I am a 1st-year M.S. student at the NLP Group at Fudan University. Before that, I received my B.Eng. from Chongqing University in 2022.

Google Scholar  /  Github  /  Twitter  /  Zhihu

profile photo
News
  • [Nov. 2022] Under the leadership of my senior Tianxiang Sun, my first paper is accepted to EMNLP 2022!
  • [Sep. 2022] I joined the NLP Group at Fudan University as a M.S. student.
  • [Jun. 2022] I received B.Eng. from College of Computer Science, Chongqing University. GPA: 3.93/4.0 (top 0.1%)
  • [Nov. 2021] With the help of Qianchen, I built a benchmark website named ELUE which is a part of one NAACL 2022 paper.
BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
Tianxiang Sun*, Junliang He*, Xipeng Qiu, Xuanjing Huang
EMNLP, 2022  
pdf / code /

We demonstrate that popular PLM-based metrics exhibit significantly higher social bias than traditional metrics. In addition, we develop debiasing adapters mitigating bias in PLM-based metrics while retaining high performance for evaluating text generation.

Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
Xiangyang Liu*, Tianxiang Sun*, Junliang He, Jiawen Wu, Lingling Wu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, Xipeng Qiu
NAACL, 2022  
pdf / code / benchmark /

We propose a benchmark, ELUE (Efficient Language Understanding Evaluation), for efficient NLP models and a strong baseline/backbone pre-trained model, ElasticBERT.