Yitong LI

Curriculum Vitae

Ph.D
School of Computing and Information Systems
The University of Melbourne
Victoria 3010, Australia

E-mail: yitongl4 [at] student [dot] unimelb [dot] edu [dot] au
Desk: Desk 7, Lv. 3, DMD (B168)

Welcome to my homepage!
I recieved my Ph.D at School of CIS, The University of Melbourne, supervised by Prof. Tim Baldwin and Prof. Trevor Cohn.
My research interests are in Natural Language Processing (NLP) and Machine Learning.
I am now working on Privacy and Adversarial Learning with NLP applications.

What's New !

Mar. 2022 preprint PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model
preprint
Feb. 2022 2 paper accepted to ACL 2022 RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion
ACL 2022, Long
Compilable Neural Code Generation with Compiler Feedback
Findings of ACL 2022, Long

Experiences

Education

2015 - 2020 Ph.D Student of Engineering
School of Computing and Information Systems, The University of Melbourne, Victoria, Australia.
2011 – 2015 B.S. in Engineering
Computer Science and Technology (SJTU ACM Honored Class), Zhiyuan College, Shanghai Jiao Tong University, Shanghai, China.

Professional

Nov. 2020 – Nov. 2022 Visiting Scholar
Huawei Noah's Ark Lab, Huawei, Shenzhen, China
Sep. 2019 – Nov. 2019 Tutor
Statistic Machine learning
School of Computing and Information Systems, University of Melbourne, VIC, Australia
May 2019 – Jul. 2019 Tutor
Machine learning
Melbourne Business School, University of Melbourne, VIC, Australia
Nov. 2015 – Jun. 2020 Research Student
School of Computing and Information Systems, The University of Melbourne, Victoria, Australia
Aug. 2014 – Feb. 2015 Research Assistant Full-time Intern
Visual Computing Group, Microsoft Research Asia, Beijing, China
Jul. 2014 Visiting Student
The Summer Education Research Project
Department of Computer Science, Cornell University, NY, U.S.A.
Jun. 2012 – Oct. 2015 Research Student
Center for Brain-like Computing and Machine Intelligence, Shanghai Jiao Tong University, Shanghai, China
Feb. - Jun. 2014
Spring Semester 		Teaching Assistant
Set Theory and Logic for Computing Science
Shanghai Jiao Tong University, Shanghai, China

Service

2018, 2019 Student Volunteer
ACL 2018, ACL 2019
2017, 2018 Student Representative
Australasian Language Technology Association

Miscellaneous

2008 – Present Membership
Red Cross China
18th – 24th Aug. 2013 Intern
Global Finance Internship Program
Fxcm Asia Limited, Hong Kong

Publications


2022
  • Fei Mi, Yitong Li, Yulong Zeng, Jingyan Zhou, Yasheng Wang, Chuanfei Xu, Lifeng Shang, Xin Jiang, Shiqi Zhao, Qun Liu (2022) PanGu-Bot: Efficient Generative Dialogue Pre-training from Pre-trained Language Model, In (preprint)
  • Xinyan Zhao, Bin He, Yasheng Wang, Yitong Li, Fei Mi, Yajiao Liu, Xin Jiang, Qun Liu, Huanhuan Chen (to appear) UniDS: A Unified Dialogue System for Chit-Chat and Task-oriented Dialogues, In (ACL workshop DIALDOC 2022, full paper)
  • Kai Chen, Ye Wang, Yitong Li, Aiping Li (to appear) RotateQVS: Representing Temporal Information as Rotations in Quaternion Vector Space for Temporal Knowledge Graph Completion, In (ACL 2022, full paper)
  • Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, jin liu, hao wu, Xin Jiang, Qun Liu (to appear) Compilable Neural Code Generation with Compiler Feedback, In (Findings of ACL 2022, Long paper)
  • Jingyan Zhou, Jiawen Deng, Fei Mi, Yitong Li, Yasheng Wang, Minlie Huang, Xin Jiang, Qun Liu, Helen Meng (2022) Towards Identifying Social Bias in Dialog Systems: Frame, Datasets, and Benchmarks, In (preprint, full paper)
  • Yihe Wang, Yitong Li, Yasheng Wang, Fei Mi, Pingyi Zhou, Xin Wang, Jin Liu, Qun Liu, Xin Jiang (2022) Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation, In (preprint, full paper)
  • Fei Mi, Yitong Li, Yasheng Wang, Xin Jiang, Qun Liu (to appear) CINS: Comprehensive Instruction for Few-shot Learning in Task-oriented Dialog Systems, In (AAAI 2022, full paper)

    • 2021
  • Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li, Gholamreza Haffari and Qun Liu (2021) Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training, In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021, long paper)
  • Kai Chen, Ye Wang, Yitong Li, Aiping Li, Xiaojuan Zhao(2021) Contextualise Entities and Relations: An Interaction Method for Knowledge Graph Completion, In Proceedings of the 30th International Conference on Artificial Neural Networks (ICANN 2021)

    • 2020
  • Lingjuan Lyu, Xuanli He and Yitong Li (to appear) Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and Fairness, In Findings of EMNLP 2020
  • Lingjuan Lyu, Yitong Li, Karthik Nandakumar, Jiangshan Yu and Xingjun Ma (2020) How to Democratise and Protect AI: Fair and Differentially Private Decentralised Deep Learning, IEEE Transactions on Dependable and Secure Computing, 10.1109/TDSC.2020.3006287
  • Lingjuan Lyu, Jiangshan Yu, Karthik Nandakumar, Yitong Li, Xingjun Ma, Jiong Jin, Han Yu, and Kee Siong Ng (to appear) Towards Fair and Privacy-Preserving Federated Deep Models, IEEE Transactions on Parallel and Distributed Systems, vol. 31, no. 11, pp. 2524-2541, 10.1109/TPDS.2020.2996273
  • Lingjuan Lyu, Yitong Li, Xuanli He and Tong Xiao (2020) Towards Differentially Private Text Representations, In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, Xi'an, China, pp. 1813--1816.

    • 2019
  • Li, Yitong, Timothy Baldwin and Trevor Cohn (2019) Semi-supervised Stochastic Multi-Domain Learning using Variational Inference, In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp. 1923--1934.
  • Yitong Li (2019) Towards Robust Representation of Natural Language Processing, UOM PhD Thesis

    • 2018
  • Li, Yitong, Timothy Baldwin and Trevor Cohn (2018) Towards Robust and Privacy-preserving Text Representations, In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (ACL 2018, Volume 2: Short Papers), Melbourne, Australia, pp. 25--30.
  • Doris Hoogeveen, Andrew Bennett, Yitong Li, Karin Verspoor and Timothy Baldwin (2018) Detecting Misflagged Duplicate Questions in Community Question-Answering Archives, In Proceedings of the 12th International AAAI Conference on Web and Social Media (ICWSM-18), Stanford, USA, pp. 112--120.
  • Li, Yitong, Timothy Baldwin and Trevor Cohn (2018) What's in a Domain? Learning Domain-Robust Text Representations Using Adversarial Training, In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies (NAACL HLT 2018), New Orleans, USA, pp. 474--479.

    • 2017
  • Li, Yitong, Trevor Cohn and Timothy Baldwin (2017) BIBI System Description: Building with CNNs and Breaking with Deep Reinforcement Learning, In Proceedings of the EMNLP 2017 Workshop on Building Linguistically Generalizable NLP Systems (BLGNLP 2017), Copenhagen, Denmark, pp. 27--32.
  • Li, Yitong, Trevor Cohn and Timothy Baldwin (2017) Robust Training under Linguistic Adversity, In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2017, short paper), Valencia, Spain, pp. 21--27.

    • 2016
  • S. Shivashankar, Yitong Li and Afshin Rahimi (2016) Filter and Match Approach to Pair-wise Web URI Linking, In Proceedings of the Australasian Language Technology Association Workshop 2016 (ALTA 2016), Melbourne, Australia, pp. 181--185
  • Li, Yitong, Trevor Cohn and Timothy Baldwin (2016) Learning Robust Representations of Text, In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP 2016, short paper), Austin, Texas, USA, pp. 1979--1985.
  • Hoogeveen, Doris, Yitong Li, Huizhi Liang, Bahar Salehi, Timothy Baldwin and Long Duong (2016) UniMelb at SemEval-2016 Task 3: Identifying Similar Questions by Combining a CNN with String Similarity Measures, In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval 2016), San Diego, USA, pp. 776--781.

    • 2015
  • Li, Yitong, Rui Wang and Hai Zhao (2015) A Machine Learning Method to Distinguish Machine Translation from Human Translation, In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (PACLIC 29), Shanghai, China, pp. 354--360

    • Miscellaneous Issues

  • Li, Yitong (2015)《毕业感悟》. 《致远毕业纪念册》, Shanghai Jiao Tong University Press
  • Li, Yitong (2015)《致远之于我》. 《致远逐梦》 , pages 221–223, isbn 978-7-313-10936-1, Shanghai Jiao Tong University Press
  • Li, Yitong (2011)《我的故事》. 《携手·上海交通大学ACM班十年风雨路》 , isbn 978-7-313-08536-8, Shanghai Jiao Tong University Press

    • Awards & Honors

    Mar. 2019 Conference Travel Scholarships, School of Computing and Information System, The University of Melbourne
    May 2018 Google PhD Travel Scholarship, Google
    Jul. 2017 1st as Builder & 3rd as Breaker, Build It Break It: The Language Edition
    Mar. 2017 Conference Travel Scholarships, School of Engineering, The University of Melbourne
    Mar. 2017 1st Place, Jane Street ETC Melbourne
    Nov. 2016 2nd Place, ALTA Shared Task 2016
    Oct. 2016 Google PhD Travel Scholarship, Google
    May 2016 3rd Place, Melbourne Data Science Student Challenge
    Mar. 2016 1st Place, Microsoft College Code Competition @The University of Melbourne
    Nov. 2015 Melbourne Research Scholarship
    The University of Melbourne
    Jun. 2015 Honor of Meeting the Academic Requirements of Zhiyuan College Top honor for SJTU undergraduate
    Shanghai Jiao Tong University
    Mar. 2015 Stars of Tomorrow Internship Program Award, Microsoft Research Asia
    2013 SJTU Academic Year University Scholarship of Shanghai Jiao Tong University, Shanghai Jiao Tong University
    2012 SJTU Academic Year University Scholarship of Shanghai Jiao Tong University, Shanghai Jiao Tong University
    Nov. 2010 & 2009 & 2008 1 st Prizes top 5/1000+, National Olympiad Informatics in Provinces, China
    2009 Tenth highest Level of Grading Test Certificate of Piano, Nanjing University of the Arts, China
    --- Grade Examination of Musical Level 10 highest level for non-professionals of Keyboard

    Random Projects

    This page is about my projects that I am or was working on.
    You can find code pieces of some on my Github.

    Research Projects

    • Research Impact @Unimelb, 2017
      Unimelb Projects
    • Denoising and Beautification for Burst Camera Selfies on Smartphone @MSRA, 2015
      Mentored by Researcher Lu Yuan
    • Whiteboard and Document Detection @MSRA, 2014
      Mentored by Researcher Lu Yuan and co-operated with Researcher Jiangyu Liu
      Products related: Office Lens.
    • Solving Low-rank Semi-definite Programming Problem @Cornell, 2014
      With Hang Wu, supervised by Prof. John E. Hopcroft

    Competition Projects

    You can also find a banch of coursework projects on my github if you are interested in them.

    Personal Interests

    Here are my personal interests and maybe a short description for them.
    This section is only about my lift without research, and you are welcome to go to me about them.

      Music & Instruments

      I am a fan of classic
    • Piano (Tenth Level top of Grading Test Certificate)
    • Keyboard (Grade Examination of Musical Level 10 top for non-professionals)
    • Trumpet (Participated in the Orchestra of School and local gala)
    • Guitar, Harmonica
    • Also, I am(was) playing many music games, such as, OSU, Jubeat and Guitar Heroes

      • History

    • Interested in Ancient Greek, Roman and Medieval
    • Mythologies and Origins

      • Sports

      I do snow sports (ski & snowboard) in winter, and diving (SCUBA) and surfing in summar!