About Me

Hi~ I am Tianyu Gao, a third-year undergraduate student from the Department of Computer Science and Technology, Tsinghua University. I am advised by Professor Zhiyuan Liu and affiliated with Tsinghua Natural Language Processing and Computational Social Science Lab (THUNLP). My research interests lie within the intersection of natural language processing, deep learning, information extraction and knowledge graphs.

[My CV] [THUNLP github]

Publications

Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification
Tianyu Gao*, Xu Han*, Zhiyuan Liu and Maosong Sun. (* indicates equal contribution)
To appear in proc. 33rd AAAI Conference on Artificial Intelligence, 2019

  • Tackle the problem of few-shot relation classification in noisy scenario.
  • Add instance-level attention and feature-level attention to Prototypical Networks.
  • Achieve great improvement on accuracy and convergence speed compared to baseline models.

Projects

OpenNRE: An Open-Source Package for Neural Relation Extraction

Project Link: https://github.com/thunlp/OpenNRE

  • Provide an easy-to-modify framework for relation extraction.
  • Implement several neural methods for relation extraction.

NREPapers: A Paper List for Neural Relation Extraction

Project Link: https://github.com/thunlp/NREPapers

  • Include important papers in relation extraction and will continue to be updated.

FewRel: FewRel Dataset, Toolkits and Baseline Models

Project Link: https://github.com/thunlp/fewrel

  • FewRel is a large-scale few-shot relation extraction dataset.
  • I helped with implementing the toolkits and several baseline models.

Experiences

Tsinghua Natural Language Processing and Computational Social Science Lab

As undergraduate student. Jan. 2018 - Present

  • Under the guidance of Prof. Zhiyuan Liu.

Momenta

As intern. May 2017 - May. 2018

  • Research on semantic segmentation.