Wei Zhao (赵伟)

He is a final year PhD student at Technische Universität Darmstadt, Germany, in the graudate school of AIPHES, led by Iryna Gurevych. Previously, he was a NLP research scientist at Tencent Cloud. He studied his master in Computer Science at University of Chinese Academy of Sciences and studied his bachelor in Linguistics at Fudan University.

He had research stays, two months each at University of Copenhagen, University of Mannheim and Nanyang Technological University, worked with Isabelle Augenstein, Goran Glavaš​ and Erik Cambria.

He is co-organizing the 1st annual Evaluation and Comparison of NLP Systems workshop, co-located in EMNLP2020.

His current research interests include text quality estimation, cross-lingual representations, discourse and information theory and generative modeling. His research is funded by German Research Foundation.

He has an Erdős number of 3.

Email: zhao(at)aiphes.tu-darmstadt.de
Google Scholar | Github | Twitter | Medium



News

  • I will be on the job market in 2021 and am looking for a postdoc or a research position in industry.
  • 11/2020 We will organize the 2nd annual Eval4NLP workshop at EMNLP 2021
  • 09/2020 One paper accepted at CODI (discourse) workshop at EMNLP 2020
  • 04/2020 Two papers accepted at ACL 2020
  • 11/2019 Give a talk at University of Mannheim, Germany
  • 11/2019 We will organize Eval4NLP workshop at EMNLP2020
  • 10/2019 Attend EurNLP summit, Facebook, London
  • 08/2019 One paper accepted at CIKM 2019
  • 08/2019 One paper accepted at EMNLP 2019 (oral)
  • 07/2019 One paper accepted at ACL 2019 (oral)
  • 06/2019 Attend Google NLP summit, Zürich
  • 01/2019 Give a talk at University of Padova, Italy
  • 01/2019 One paper accepted at AAAI 2019 (oral)
  • 08/2018 One paper accepted at EMNLP 2018 (oral)
  • 07/2018 Give a talk at Top Data Science Seminar, Helsinki
  • 05/2018 Give a talk at Tencent AI summit, Shenzhen, China
  • 05/2018 Two papers accepted at IJCAI 2018 (orals)

Recent Publication

  • Inducing Language-Agnostic Multilingual Representations
    Wei Zhao, Steffen Eger, Johannes Bjerva, Isabelle Augenstein
    Arxiv, 2020
    [paper] [code]
  • Evaluation of Coreference Resolution Systems Under Adversarial Attacks
    Haixia Chai, Wei Zhao, Steffen Eger, Michael Strube
    CODI, EMNLP workshop, 2020
    [paper]
  • On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation
    Wei Zhao, Goran Glavaš, Maxime Peyrard, Yang Gao, Robert West, Steffen Eger
    ACL, 2020
    [paper] [code]
  • SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization
    Yang Gao, Wei Zhao, Steffen Eger
    ACL, 2020
    [paper] [code]
  • Evaluating Machine Translation without Human References Using Cross-lingual Encoders
    Wei Zhao, Yang Gao, Steffen Eger
    EurNLP, 2019
    [paper]
  • MoverScore: Text Generation Evaluating with Contextualized Embeddings and Earth Mover Distance
    Wei Zhao, Maxime Peyrard, Fei Liu, Yang Gao, Christian M. Meyer, Steffen Eger
    EMNLP, 2019
    [paper] [code]
  • Towards Scalable and Reliable Capsule Networks for Challenging NLP Applications
    Wei Zhao, Haiyun Peng, Steffen Eger, Erik Cambria, Min Yang
    ACL, 2019
    [paper] [code]
  • Investigating Capsule Networks with Dynamic Routing for text classification
    Wei Zhao, Jianbo Ye, Min Yang, Zeyang Lei, Suofei Zhang, Zhou Zhao
    EMNLP, 2018
    [paper] [code]

Recent Reward

  • Facebook Travel Award, London, 2019
  • AthNLP Scholarship, Greece, 2019
  • NAACL Outstanding Reviewer, 2019
  • Google Travel Award, Zurich, 2019
  • German PhD Funding, 2018
  • IJCAI Travel Award, 2018

Teaching

  • Deep Learning for Natural Language Processing, TU Darmstadt, 2019, 2020
  • Foundations of Language Technology, 2020

Professional Service

  • Conference Reviewer: SIGIR18, NAACL19, ACL19, EMNLP19, NeurIPS19, CoNLL19, AAAI19
  • Journal Reviewer: IEEE Transactions on Multimedia, Transactions on Asian and Low-Resource Language Information Processing

Languages

  • Chinese: Native
  • English: Working professional proficiency
  • German: Limited working proficiency