Email: ands691119@gmail.com, Github, Zhihu

Biography

I graduated from Hunan University with an undergraduate degree in Electrical Engineering and Automation. My supervisor was Prof. Zhigang Ling who start my research journey about Artificial Intelligence.

In China (2019/09-2020/01; 2022/02-2022/06), I researched on low resources language at China and National Language Resource and Monitoring Research Center in Minzu University of China, advised by Prof. Xiaobing Zhao and Prof. Yuan Sun. In the UK ( 2021/02-2022/01), My major is Big Data Science at Queen Mary University of London. During my stay in the UK, I am doing research on machine reading comprehension at School of Electronic Engineering and Computer Science, advised by Ph.D. candidate Rosella Galindo Esparza.

Recently I am working on generative pre-trained language model at ICT(Institute of Computing Technology, Chinese Academy of Sciences), supervised by Prof. Xishan Zhang.

In open-source contributions, I like to share something that I think is valuable. Now I am the project leader of an open source project about data analysis(Hands-on data analysis), which now has 400 starts and 163 forks.

Recent progress💡

1. Recently, I am working as a NLP Research Intern at ICT(Institute of Computing Technology, Chinese Academy of Sciences), mainly working on generative pre-trained language model.
2. In collaboration with Rosella Galindo Esparza in Queen Mary University of London, a paper is being written on low-resource machine reading comprehension. The paper will be submitted to ACL.

Research Interests

• Artificial Intelligence
• Computational Linguistics
• Natural Language Processing
• Machine Reading Comprehension
• Language Model

Professional Services

• Reviewer: IEEE Transactions on Affective Computing(IF>10)

Publications

1. Improving Low-resource Question Answering by Augmenting Question Information (Detail, Pdf)

   Under Review ACL 2022

   Andong Chen, Yuan Sun, Xiaobing Zhao, Rosella P. Galindo Esparza

2. A Joint Model for Representation Learning of TibetanKnowledge Graph Based on Encyclopedia (Detail, Pdf)

   Yuan Sun, ** Andong Chen ** (Equal Contribution), Chaofan Chen, Tianci Xia, Xiaobing Zhao

   The Transactions on Asian and Low-Resource Language Information Processing, 2021

3. JCapsR: A joint capsule neural network learning model for Tibetan language knowledge graph (Detail, Pdf)

   Yuan Sun, Jiaya Liang, Andong Chen Xiaobing Zhao

   The Twentieth China National Conference on Computational Linguistics, CCL, ACL Anthology, 2021

Patents

1. A service system for automatic generation of reading questions in Tibetan language for elementary school (CN202110228195.5)
2. A representation method for Tibetan knowledge base (Submitted)

Talks

• Alibaba Could-TianChi: Speech Recognition Novice Competition (Slide, Video)

  June 30, 2021

  Invited Talk at Alibaba Could-TianChi-Novice Competition, Beijing

• Bert and Machine Reading Comprehension (Slide, Video)

  July 28, 2021

  Invited Talk at Datawhale and Graviti, Beijing

• Open-source: Open source yourself (Slide)

  Oct 02, 2021

  Invited Talk at Institute of Computing Technology, Chinese Academy, Beijing

• WhalePaper: ERNIE 3.0 (Slide)

  August 10, 2021

  Invited Talk at WhalePaper, Beijing

• Transformer-Position (Slide)

  August 24, 2021

  Invited Talk at Institute of Computing Technology, Chinese Academy, Beijing

Open Source Contribution

• Hands-on data analysis✨
  • Role: Project sponsor and content builder
  • Time: 2019/01-2019/05
  • Introduction: An open-source data analysis project for everyone to learn by themselves
  • Github, 400 Stars, 163 Forks
• Food Voice Recognition(Alibaba-Tianchi-Match)
  • Role：Competition designer and content builder
  • Time: 2021/01-2021/05
  • Introduction: Datawhale and Alibaba-Tianchi Co-Sponsor Basic Data Science Competition
  • Competition, Baseline, Slide, Video
• Dcoker-Team-Learning
  • Role: Content builder
  • Time: 2021/01-2021/03
  • Introduction: This tutorial is a collaborative project with “docker from beginner to practice”, and we have reorganized and refactored it based on the original project with the permission of the author
  • Github, 454 Stars, 302 Forks
• Thorough-pytorch
  • Role: Content builder
  • Time: 2021/07-Present
  • Introduction: Through team learning, you will be able to master the basic knowledge and content of PyTorch from shallow to deep
  • Github, 454 Stars, 302 Forks

Intership Experience

• Summer 2021: NLP Research Intern
  • Institute of Computing Technology, Chinese Academy of Sciences
  • Cambricon Technologies Corporation
  • Main Work: Build a generative pre-trained language model
  • Supervisor: Prof. Xishan Zhang
• Spring 2021: NLP Research——Final Project
  • Queen Mary University of London
  • Main Work: Research low-resource language machine reading comprehension
  • Supervisor: Ph.D. Rosella Galindo Esparza
• Summer 2019: Could Computing Intern
  • Sangfor Technologies Inc.
  • Main Work: Desktop Cloud Development

Honors and Awards

• “Huawei Cup” China Post-Graduate Mathematical Contest in Modeling(17th), Third Prize(15%), The Chinese Society of Academic Degrees and Graduate Education, 2020
• China College Students’ ‘Internet+’Innovation and Entrepreneurship Competition(6th), Third Prize(25%), Beijing Municipal Education Commission, 2020
• WeBank’s fintech university competition(2th), Top 10(10/100), WeBank & Shenzhen University WeBank Institute of Fintech, 2020
• Third Prize Scholarship (10%), Mizu University of China, 2019-2020

Misc.

I hiked 30.8 kilometers of the Silk Road in the summer after College Entrance Examination. I like the feeling of slowly moving forward and seeing the scenery along the way, and looking back to see how far I have moved forward. During college I enjoyed making friends and interacting with all differnet kinds of people. Communication has become a way for me to relax. I also like to communicate when I am alone, reading books and watching movies are the most common things I do.

For sports, I like swimming and badminton. I am recently learning cue sports.