Jun Yan

Ph.D. Student

Department of Computer Science
University of Southern California

About Me

I am a first-year PhD student at University of Southern California (USC). I am fortunately advised by Prof. Xiang Ren. My research focuses on Natural Language Processing and Machine Learning. I am currently interested in how to leverage external knowledge to benefit machine learning models, especially in low-resource scenarios.

You can find my CV here.

Publications

Learning from Explanations with Neural Module Execution Tree

Ziqi Wang*, Yujia Qin*, Wenxuan Zhou, Jun Yan, Qinyuan Ye, Leonardo Neves, Zhiyuan Liu, Xiang Ren (* indicates equal contribution)

In Proceedings of ICLR 2020 [code]

Learning Dual Retrieval Module for Semi-supervised Relation Extraction

Hongtao Lin, Jun Yan, Meng Qu, Xiang Ren

In Proceedings of TheWebConf 2019 [code]

Language Modeling with Sparse Product of Sememe Experts

Yihong Gu*, Jun Yan*, Hao Zhu*, Zhiyuan Liu, Ruobing Xie, Maosong Sun, Fen Lin, Leyu Lin (* indicates equal contribution)

In Proceedings of EMNLP 2018 [code]

Research Experience

MSIIP Lab

Undergraduate Research Assistant

Oct 2018 - Jun 2019

Multimedia Signal and Intelligent Information Processing Lab at Tsinghua University
Advisor: Prof. Ji Wu

I worked on my thesis project, which focuses on machine translation in the low-resource medical domain. I improved the performance by leveraging both in-domain terminology constraints and out-domain training data.

INK Lab

Graduate Research Assistant

Aug 2019 - Present

Undergraduate Research Assistant

Jul 2018 - Sep 2018

Intelligence and Knowledge Discovery Research Lab at University of Southern California
Advisor: Prof. Xiang Ren

Inspired by the duality between relation extraction and sentence retrieval with relation query, we proposed a semi-supervised dual learning framework that can better leverage unlabeled data than traditional methods.

I am now working on incorporating knowledge graph into knowledge-driven tasks like quesion answering.

NLP Lab

Undergraduate Research Assistant

Nov 2017 - Apr 2018

Natural Language Processing Lab at Tsinghua University
Advisor: Prof. Zhiyuan Liu

We proposed a language model that incorporates sememe (the basic semantic unit) knowledge about words and demonstrated its superior performance and interpretability on language modeling and its downstream task.

Honors & Awards

  • Sep 2019: My project receives support from Abode Data Science Research Award ($50,000), PI: Prof. Xiang Ren
  • Aug 2019: Annenberg Fellowship, University of Southern California
  • Jul 2019: Excellent Graduate, Tsinghua University
  • Oct 2018: Evergrande Scholarship, Tsinghua University
  • Oct 2017: Samsung Scholarship, Tsinghua University
  • Oct 2016: JJWorld Scholarship, Tsinghua University

Education

University of Southern California

Ph.D. in Computer Science

2019 - Present     Los Angeles, U.S.

Tsinghua University

B.Eng. in Electronic Engineering

2015 - 2019     Beijing, China