Tianlu Wang (王天露)

Contact me

  • E-mail: tianlu[at]virginia[dot]edu
  • Address: 430 Rice Hall, Charlottesville, VA.
  • [curriculum vitae]

Hi! I am a PhD student at the Department of Computer Science, University of Virginia, from 16Fall. I am fortunate to work with my advisor, Prof. Vicente Ordóñez Román . Before coming to UVa, I obtained my bachelor degree in computer science from Zhejiang University, China. I have a broad interest in exploring topics concerning fairness, robustness and accountability in machine learning models, especially in computer vision and natural language processing systems.

Publications

Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations
Tianlu Wang, Jieyu Zhao, Mark Yatskar, Kai-Wei Chang, Vicente Ordonez.
International Conference on Computer Vision. ICCV 2019. Seoul, South Korea. October 2019.
[arxiv] [bibtex]

Gender Bias in Contextualized Word Embeddings
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Ryan Cotterell, Vicente Ordonez, Kai-Wei Chang.
North American Chapter of the Association for Computational Linguistics. NAACL 2019. short.
Minneapolis, Minnesota. June 2019. (~Oral presentation)
[arXiv][bibtex]

Feedback-prop: Convolutional Neural Network Inference under Partial Evidence
Tianlu Wang, Kota Yamaguchi, Vicente Ordonez
Intl. Conference on Computer Vision and Pattern Recognition. CVPR 2018. Salt Lake City, Utah. June 2018.
[arXiv][code] [bibtex]

Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang.
North American Chapter of the Association for Computational Linguistics. NAACL 2018. short.
New Orleans, Louisiana. June 2018.
[arXiv] [code] [bibtex]

Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
Jieyu Zhao, Tianlu Wang, Mark Yatskar, Vicente Ordonez, Kai-Wei Chang.
Empirical Methods in Natural Language Processing. EMNLP 2017. Copenhagen, Denmark. September 2017.
[arxiv] [code] [bibtex](~Oral presentation + Best Long Paper Award!)

Name Tagging for Low-resource Incident Languages based on Expectation-driven Learning
Boliang Zhang, Xiaoman Pan, Tianlu Wang, Ashish Vaswani, Heng Ji, Kevin Knight and Daniel Marcu
North American Chapter of the Association for Computational Linguistics. NAACL 2016
[pdf]