* = equal contribution.

# = student/intern collaborator.

Following papers are under the CC BY 4.0 license, unless otherwise noted.

Google Scholar

Reviewer/PC Member: ACL, EMNLP (outstanding '21), NAACL-HLT, EACL, ACL Rolling Review, NLPCC, ACM TALLIP, TACL, IEEE T-PAMI.

Multimodal Pretraining:

• On the Language Encoder of Contrastive Cross-modal Models.
  Preprint 2023.
  Mengjie Zhao, Junya Ono, Zhi Zhong, Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Wei-Hsiang Liao, Takashi Shibuya, Hiromi Wakaki, Yuki Mitsufuji


• Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association .
  Preprint 2023.
  Qiyu Wu#, Mengjie Zhao, Yutong He, Lang Huang, Junya Ono, Hiromi Wakaki, Yuki Mitsufuji

Core NLP:

• LMTurk: Few-Shot Learners as Crowdsourcing Workers.
  Findings of ACL: NAACL 2022.
  Mengjie Zhao, Fei Mi, Yasheng Wang, Minglei Li, Xin Jiang, Qun Liu, Hinrich Schütze


• Modular and Parameter-Efficient Multimodal Fusion with Prompting.
  Findings of ACL: ACL 2022.
  Sheng Liang, Mengjie Zhao, Hinrich Schütze.


• Discrete and Soft Prompting for Multilingual Models.
  EMNLP 2021 (short).
  Mengjie Zhao, Hinrich Schütze.


• A Closer Look at Few-Shot Crosslingual Transfer: The Choice of Shots Matters.
  ACL 2021.
  Mengjie Zhao*, Yi Zhu*, Ehsan Shareghi, Ivan Vulić, Roi Reichart, Anna Korhonen, Hinrich Schütze.


• Masking as an Efficient Alternative to Finetuning for Pretrained Language Models.
  EMNLP 2020.
  Mengjie Zhao*, Tao Lin*, Fei Mi, Martin Jaggi, Hinrich Schütze.


• Quantifying the Contextualization of Word Representations with Semantic Class Probing.
  Findings of ACL: EMNLP 2020.
  Mengjie Zhao, Philipp Dufter, Yadollah Yaghoobzadeh, Hinrich Schütze.


• Continual Learning for Natural Language Generation in Task-oriented Dialog Systems.
  Findings of ACL: EMNLP 2020.
  Fei Mi, Liangwei Chen, Mengjie Zhao, Minlie Huang, Boi Faltings.


• Multilingual Embeddings Jointly Induced from Contexts and Concepts: Simple, Strong and Scalable.
  Preprint 2020.
  Philipp Dufter, Mengjie Zhao, Hinrich Schütze.


• A Multilingual BPE Embedding Space for Universal Sentiment Lexicon Induction.
  ACL 2019.
  Mengjie Zhao, Hinrich Schütze.


• Embedding Learning Through Multilingual Concept Induction.
  ACL 2018.
  Philipp Dufter, Mengjie Zhao, Martin Schmitt, Alexander Fraser, Hinrich Schütze.

NLP Applications:

• Are Code Pre-trained Models Powerful to Learn Code Syntax and Semantics?.
  Preprint 2023.
  Wei Ma, Mengjie Zhao, Xiaofei Xie, Qiang Hu, Shangqing Liu, Jie Zhang, Wenhan Wang, Yang Liu


• Using Lexical and Semantic Program Features to form Generic Code Representation.
  IEEE/ACM MSR 2022.
  Wei Ma*, Mengjie Zhao*, Ezekiel Soremekun, Qiang Hu, Jie Zhang, Mike Papadakis, Maxime Cordy, Xiaofei Xie, Yves Le Traon