About Me

Freda (Haoyue) SHI

Freda (Haoyue) Shi is a final-year undergraduate student in Computer Science at Peking University and double-majored in Sociology. She is a member of the Institute of Computational Linguistics advised by Prof. Junfeng Hu. Her research interest is (general) natural language understanding with large unlabeled corpus and multimodal data.

Freda did her internship at Carnegie Mellon University (advised by Prof. Alex Hauptmann working on video understanding) and New York University (advised by Prof. Sam Bowman working on sentence representation learning). She also spent some time on her internship at Google Inc., Microsoft Research (Asia), 4th-Paradigm Inc. and Megvii Inc (Face++). She is now at Toutiao AI Lab as an undergraduate research intern, working with her excellent mentors Dr. Hao Zhou and Dr.Lei Li. She will soon start her Ph.D. pursuit at Toyota Technological Institute at Chicago in October, 2018.


  • Haoyue Shi*, Jiayuan Mao*, Tete Xiao*, Yuning Jiang and Jian Sun, "Learning Visually-Grounded Semantics from Contrastive Adversarial Samples", Accepted by 27th International Conference on Computational Linguistics (COLING 2018), August 2018. (* Equal Contribution)

  • Haoyue Shi, Xihao Wang, Yuqi Sun and Junfeng Hu, "Constructing High Quality Sense-specific Corpus and Word Embedding via Unsupervised Elimination of Pseudo Multi-sense", 11th Language Resources and Evaluation Conference (LREC 2018), May 2018.

  • Haoyue Shi, Jia Chen and Alexander G. Hauptmann, "Joint Saliency Estimation and Matching using Image Regions for Geo-Localization of Online Video", 2017 ACM International Conference on Multimedia Retrieval (ICMR 2017), June 2017. [PDF]

  • Haoyue Shi, Caihua Li and Junfeng Hu, "Real Multi-Sense or Pseudo Multi-Sense: An Approach to Improve Word Representation", 1st Workshop Computational Linguistics for Linguistic Complexity (CL4LC, associated with COLING 2016), December 2016.[PDF]

  • Shan Xu, Haoyue Shi, Xiaohui Duan, Tiangang Zhu, Peihua Wu and Dongyue Liu, "Cardiovascular Risk Prediction Method Based on Test Analysis and Data Mining Ensemble System", 2016 IEEE International Conference on Big Data Analysis (Best Paper Award), March 2016.

  • (Unpublished Manuscripts)
  • Haoyue Shi, Yuqi Sun and Junfeng Hu, Understanding and Improving Multi-Sense Word Embeddings via Extended Robust Principal Component Analysis, ArXiv Preprint. [PDF]

Selected Projects


(More facts about Freda)

  • Freda was an ACM-ICPC competitor who won two gold medals at ACM-ICPC (regional) with her teammates Chengxian Mo and Tianshi Li.

  • Freda plays Guqin. She follows Jiu-Yi School, but her style is influenced by Mr. Gong Yi a lot. She was the 13th minister of PKU Guqin Society.

  • Freda was a member of PKU amateur athletic team, with the major of 5,000-meter race. She won three gold medals at PKU athletic meetings and one gold medal at Track and Field Meeting of Beijing Universade.

  • Freda loves poetry for its irresistible beauty! She often translates poems between Chinese and English.

  • Freda loves Ludwig Wittgenstein and his theories.

  • Freda reviewed a book (Chapters of basic algorithm, data structures and mathematics) on Olympiad of Informatics, of which the author was her boyfriend Yudong (Victor) Li (a famous competitor Olympiad in Informatics and ACM-ICPC in China, known as lydrainbowcat). Click here to buy the book (in Chinese).

© 2018 Freda (Haoyue) Shi