Jiaxing Xu (徐家兴)

Automatic Drive Group
SenseTime Group Limited
Email: jiaxing_xu@outlook.com

Hi! I am a research intern in Automatic Drive Group, SenseTime Group Limited. I just graduate from College of Software, Beihang University. Before joining SenseTime, I worked as a research intern in Knowledge Computing Group, Microsoft Research Asia and a research assistant in Knowledge Engineering Group of Tsinghua University.

My research interests lie in natural language processing and data mining, especially on dialog system and graph neural network. I do believe these fields make invaluable contributions to the real world.

New!! I'm applying for PhD programs and searching for a Research Assistant position currently. Don't hesitate to contact me if you are interested.

Curriculum Vitae

Education

Beihang University

School of Software

Bachelor of Engineering, Aug. 2016 - Jul. 2020

Nanyang Technological University

School of Computer Science and Engineering

Visiting Student, Jul. 2019 - Sep. 2019

Publications

    Jiaxing Xu, Jianbin Cui, Zhaoyu Wang, Jiangneng Li, Wenge Rong and Noboru Matsuda. Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics - Human Language Technologies (NAACL-HLT'21) (submitted).

    Jiangneng Li*, Jiaxing Xu*, Cheng Long, Gao Cong. Predicting Sports Trajectory under Team Aware Situations. In Proceedings of the 27th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'21) (submitted) (* means equal contribution).

    Xinhang Li, Yong Zhang, Jiaxing Xu, Chunxiao Xing, Xia Wang and Jin Wang. IMF: Interactive Multimodal Fusion Model for Link Prediction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL'21) (submitted).

    Wei Shao, Yihan He, Shuqi Liu, Jiaxing Xu and Linqi Song. An Embedding Regularized Neural Topic Model. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL'21) (submitted).

    Yanqiu Song, Hang Su, Defang Yuan, Jiaxing Xu, Ting Gao. Venture Capital and Acquisition Performance in the Newly Public Chinese Firms. In Proceedings of the 20th European Academy of Management conference(EURAM’20).

Research

Conference Concept Graph Automatic Generation by Text Mining

Researchers always have the demand to know what areas a conference focus on and how this conference developed. Thus, we purpose a method to automatically extract keywords from every paper of a conference, construct it to a concept graph, and combine those small graphs to a concept graph of a particular conference. This framework could not only help researchers quickly understand a conference, but also help us discover new concepts.

Enhanced Meta-Learning and Active Learning for Cross-lingual Named Entity Recognition with Minimal Resources

For languages with no annotated resources, transferring knowledge from rich-resource languages is an effective solution for named entity recognition (NER). While all existing methods directly transfer from source-learned model to a target language, in this paper, we propose to fine-tune the learned model with a few similar examples given a test case, which could benefit the prediction by leveraging the structural and semantic information conveyed in such similar examples. We also present an active learning algorithm to quickly find informative samples from unlabeled data that could fast improve the performance of our model.

Combine GNN with traditional Seq2seq model to improve the performance of dialog system

The baseline method of non-task-oriented dialog system is directly imputing the goal, knowledge and conversation into the encoder without using the structure features. To enhance the performance, we consider constructing a graph based on the required knowledge and using GNN to learn the structure features of the graph. Then the GNN output is combined with the origin encoder to improve the dialog agent.

TAS-LSTM: Predicting Sports Trajectory under Team Aware Situations

In order to handle unique properties of player trajectory prediction, we deliver a two-folded research procedure in which we firstly proposed a novel LSTM model called TAS-LSTM to appropriately modeling the group feature under team aware situations. We further consider the influence of the ball’s movement and proposed a new approach.

CHITCHAT: CHat with Interactively Trained Chatbots [POSTER]

• Teaching machines to converse naturally with humans is challenging and really interesting.
• We propose a fantastic system to help people construct their own chatbots:
    • An interactive syntax tree help people to define question rules.
    • Use visualization methods to understand how to make mock sentences.
    • Use BLSTM-CRF-NER model and LSTM classifier to construct chatbot.

Automatic Generation of Smart Contracts Based on Blockchain and Natural Language Processing[PAPER]

This development selects the application scenario of the trusted deployment of the lease contract, optimizes the existing NLP model, and creates an algorithm for contract processing to automatically generate the java smart contract code and deploy it to the blockchain to supervise the transaction process in real time. The protocol and user interface automatically execute the contract content and record the behavior track in real time, thus ensuring the security and convenience of the lease transaction.

Disease NLP: Intelligent Interrogation System Based on Disease Modeling[PAPER]

Manual disease coding is time-consuming and expensive. We develop a model based on 3000 real cases and large-scale drug database. Thus, we can recommend medication to patients through their symptoms.

Professional Experience

  • SenseTime Group Limited
    Research Intern, advised by Haifang Qin
    Aug 2020 - Present
  • Knowledge Computing Group, Microsoft Research Asia
    Research Intern, advised by Börje Karlsson
    Dec 2019 - Jun 2020
  • Knowledge Engineering Group, Tsinghua University
    Research Intern, advised by Jie Tang
    Jun 2018 - Jun 2020
  • Computational Intelligence Lab, Nanyang Technological University
    Research Intern, advised by Yiping Ke
    Jul 2019 - Sep 2019
  • Big Data Mining Team, Microsoft Research Asia
    Research Intern, advised by Börje Karlsson
    Mar 2019 - Jun 2019
  • School of Software, Beihang University
    Teaching Assistant of The Practice of Programming
    Aug 2018 - Sep 2018
  • Jiuyi (Beijing) Information Technology Co., Ltd.
    R&D Engineer, Research and Development Department
    Jun 2017 - Sep 2017

Honors

  • 2019   Software College Innovation and Entrepreneurship Scholarship
  • 2019   Software College Excellent Student Leader Award
  • 2019   Yuanhang Undergraduate Summer Overseas Research Scholarship
  • 2019   3rd Prize of the 29th Feng Ru Cup Science and Technology Competition
  • 2018   Software College Innovation and Entrepreneurship Scholarship
  • 2018   3rd Prize of the 28th Feng Ru Cup Science and Technology Competition
  • 2017   Software College Excellent Student Leader Award

Community & Organization Experience

  • Student Union of Software School, Beihang University
    Minister of Public Relations Department
    Jul 2017 - Jul 2019
  • HP DreamWorks, Beihang University
    Campus Captain
    Jun 2017 - Jun 2019

Miscellaneous

Aside from my curiosity about computer science and my study preoccupation, I am also a big fan of music and go game. I would like to listen to the concert, play guitar or watch go game competition in my free time. If this involves sports, I favor swimming since it enhances my self-control and it is a benefit in my health insurance and spirit.