1. BERT Loses Patience: Fast and Robust Inference with Early Exit Wangchunshu Zhou*, Canwen Xu*, Tao Ge, Julian McAuley, Ke Xu, and Furu Wei NeurIPS 2020
    Acceptance rate: 1900/9454=20.1%
  2. BERT-of-Theseus: Compressing BERT by Progressive Module Replacing Canwen Xu*, Wangchunshu Zhou*, Tao Ge, Furu Wei, and Ming Zhou EMNLP 2020
    Acceptance rate: 754/3359=22.4%
    [arXiv] [Code]
  3. HuggingFace’s Transformers: State-of-the-art Natural Language Processing The Hugging Face Team EMNLP 2020 (Demo)
  4. MATINF: A Jointly Labeled Large-Scale Dataset for Classification, Question Answering and Summarization Canwen Xu*, Jiaxin Pei*, Hongtao Wu, Yiyu Liu, and Chenliang Li ACL 2020
    Acceptance rate: 779/3429=22.7%
    [PDF] [arXiv] [URL] [Video] [Code]
  5. Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders Yu Duan*, Canwen Xu*, Jiaxin Pei*, Jialong Han, and Chenliang Li ACL 2020
    Acceptance rate: 779/3429=22.7%
    [PDF] [arXiv] [URL] [Video] [Code]
  6. UnihanLM: Coarse-to-Fine Chinese-Japanese Language Model Pretraining with the Unihan Database Canwen Xu, Tao Ge, Chenliang Li, and Furu Wei AACL-IJCNLP 2020
    Acceptance rate: 106/375=28.3%
    (To appear)


  1. DLocRL: A Deep Learning Pipeline for Fine-Grained Location Recognition and Linking in Tweets Canwen Xu, Jing Li, Xiangyang Luo, Jiaxin Pei, Chenliang Li, and Donghong Ji WWW 2019
    Acceptance rate: 72/361=19.9%
    [arXiv] [URL]
  2. Exploiting Multiple Embeddings for Chinese Named Entity Recognition Canwen Xu*, Feiyang Wang*, Jialong Han, and Chenliang Li CIKM 2019
    Acceptance rate: 100/471=21.2%
    [arXiv] [URL] [Poster] [Slides] [Code]



  1. Obj-GloVe: Scene-Based Contextual Object Embedding Canwen Xu, Zhenzhong Chen, and Chenliang Li arXiv cs.CV 1907.01478 [arXiv]