Jian Wang (王健) PhD Student Department of Computing, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong, China Email: jian-dylan.wang (at) connect.polyu.hk   or                jwanglvy (at) gmail.com [Curriculum Vitae]   [Github]   [Google Scholar]   [Twitter]

I am a second-year PhD student at The Hong Kong Polytechnic University (PolyU), advised by Prof. Maggie Wenjie Li. Previously, I was a visiting student at SIAT, Chinese Academy of Sciences from 2018 to 2019, advised by Prof. Min Yang. I received my M.Eng. degree and B.Eng. degree from the School of Computer Science and Engineering, South China University of Technology (SCUT) in 2020 and 2017, respectively.

Research

I have broad interests in natural language processing (NLP), particularly in dialogue systems and natural language generation. I have the following long-term research goals:

• Building practical and intelligent dialogue systems. I am excited about simple and effective approaches that can be generalizable to real-world conversation scenarios.
• Developing principled methods for natural language generation. I am interested in how human knowledge (e.g., factual, commonsense, etc.) can be reasoned and used in natural language generation.

Recently, I've become interested in goal-directed dialogue systems, which aim to proactively direct a dialogue toward a pre-determined target.

Selected Publications (Full List)

2023

• COLA: Improving Conversational Recommender Systems by Collaborative Augmentation.
  Dongding Lin*, Jian Wang*, and Wenjie Li.     (*: Equal Contribution)
  AAAI Conference on Artificial Intelligence (AAAI), 2023.
  [arXiv] [code]

Preprint

• Follow Me: Conversation Planning for Target-driven Recommendation Dialogue Systems.
  Jian Wang, Dongding Lin, and Wenjie Li.
  arXiv preprint arXiv:2208.03516, 2022
  [arXiv] [code]

2021 and Before

• Template-guided Clarifying Question Generation for Web Search Clarification.
  Jian Wang and Wenjie Li.
  ACM International Conference on Information and Knowledge Management (CIKM), 2021.
  [paper] [slides] [code]

• Dual Dynamic Memory Network for End-to-End Multi-turn Task-oriented Dialog Systems.
  Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, and Min Yang.
  International Conference on Computational Linguistics (COLING), 2020.
  [paper] [code]

• Improving Knowledge-aware Dialogue Generation via Knowledge Base Question Answering.
  Jian Wang, Junhao Liu, Wei Bi, Xiaojiang Liu, Kejing He, Ruifeng Xu, and Min Yang.
  AAAI Conference on Artificial Intelligence (AAAI), 2020.
  [arXiv] [paper] [code]

• Topic Discovery by Spectral Decomposition and Clustering with Coordinated Global and Local Contexts.
  Jian Wang, Kejing He, and Min Yang.
  International Journal of Machine Learning and Cybernetics (JMLC), 2020.
  [paper] [PDF]

Experiences

• 2020/11 - 2021/08: Research assistant at PolyU (Advisor: Prof. Maggie Wenjie Li)
• 2020/07 - 2020/10: Research intern at Rulai Inc. (Advisor: Dr. Yi Zhang)
• 2018/08 - 2019/09: Visiting student at SIAT, Chinese Academy of Sciences (Advisor: Prof. Min Yang)

Competitions

• [2021/06] Third Prize of 2021 Baidu Language and Intelligence Challenge: Multi-skill Dialogue
• [2018/12] Third Prize of Byte Cup 2018 International Machine Learning Contest
• [2017/10] Ranked 50th Worldwide on IEEE Xtreme 11.0 Programming Competition
• [2016/05] Shenzhen Area Site Bronze Medal of 2016 HUAWEI Code Craft

Professional Activities

Teaching Assistant

• TA for COMP 6709: Advanced Natural Language Processing, Spring 2023 | 2022, PolyU
• TA for COMP 2021: Object-Oriented Programming, Fall 2022 | 2021, PolyU
• TA for Design and Analysis of Algorithm, Spring 2018, SCUT
• TA for Advanced Language Program Design (C++), Fall 2017, SCUT

Conference Reviewer

• EMNLP'22, COLING'22, EMNLP'21, COLING'20

Open-Source Projects

• 📖 Paper-Reading: Reading list in dialogue systems and natural language generation (constantly updating 🤗).
• 🐳 PyLoader: An asynchronous Python dataloader for loading big datasets.

Useful Resources

• ⏳ AI Conference Deadlines: Countdowns to top CV/NLP/ML/Robotics/AI conference deadlines.
• 📝 Writing Perfect Papers: A long talk on how to write perfect papers (by Prof. Baochun Li @UofT).
• 📰 Sebastian Ruder's Blog: Sebastian Ruder's blog with deep insights about NLP/ML/DL.
• 🍑 Lilian Weng's Blog: Lilian Weng's blog with broad learning notes about DL/NLP.
• 📸 Jay Alammar's Blog: Visualizations and animations for many language models (Transformer, BERT, etc).
• 📡 Scientific Spaces: Jianlin Su's blog (in Chinese) about ML|NLP theories with deep explorations.
• 👩‍🎓 Global Equality for PhDs: Resources to help global equality for PhDs in NLP/AI.

Misc.

• I enjoy Chinese calligraphy and most outdoor sports (especially basketball, table tennis, and badminton). I also spend my leisure time on variety shows, literature books, and movies.

• I dream of traveling around China and many places around the world someday.