Breif Bio

— NLP as well as Deep Learning could not only help machines better understand human beings , but also help us to know ourselves better.

My name is xu shiting(许士亭) or will xu, reasearch in NLP or data mining related area.

I am a lecturer at Department of Cyberspace Security in Shandong University of Political Science and Law.

My research interests are machine learning, NLP, Deep Learning and Data Mining. I think those researching areas provide us with new lights to perceive data we have and the world we live. So I am very interested in erecting novel models and admiring effects it bring to the world. I have also worked on Information Security related to malicious software classification before.

[Contact]   [CV]

---

News!!!

• ⏰ 2022-09-01 🕍 I am a lecturer at Department of Cyberspace Security in Shandong University of Political Science and Law.

---

Publications

• 2021   Xu, Shiting, et al. Automatic Task Requirements Writing Evaluation via Machine Reading Comprehension. International Conference on Artificial Intelligence in Education. Springer, Cham, 2021.   [pdf]   conference

• 2020   Xu, Shiting, Wenbiao Ding, and Zitao Liu. Automatic dialogic instruction detection for k-12 online one-on-one classes. International conference on artificial intelligence in education. Springer, Cham, 2020.   [pdf]   conference

• 2017   Xu, Shiting, Xinyu Ma, Yuandong Liu, and Qiang Sheng. Malicious Application Dynamic Detection in Real-Time API Analysis. In 2016 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), pp. 788-794. IEEE, 2016. [pdf]   conference

---

Working

• 2021.09 - 2022.07   Du Xiao Man (Beijing, China)
  • Responsible for NLP infrastructure. Focused at Chinese Word Segmentation Task.

• 2019.08 - 2021.09   Tomorrow Advanced Life (Beijing, China)
  • Working on Chinese writing judgement system. Developed Chinese word Correction model based on pre-triained language model.
  • Working on Enlighs writing evaluation, responsible for the whole system. And personally focused at English Grammar Correction task. Developed a English Grammar Correction model based on Transformer architecture. Also build an prompt writing task evaluation model based on MRC technology.

• 2017.09 - 2018.11   Pachira Information Technology Beijing Co., Ltd.
  • Improved Role accuracy of results of speech translation model with seq2seq model based on semantic information.
  • Participated in building a system based on the Question-Answer model to extract user information from conversations.

• 2017.03 - 2017.07   Kaspersky Lab, Beijing, China  (Intership)
  • Designed a malicious software’s families classification model based on CNN.     [Details]
  • Implemented a CS system (based on tornado) to help analysts to train and invoke the model.

---

Education

• 2014.09 - 2017.03   Master of Science, School CyberSpace Security(Former School of Computer Science), BeiJing University of Posts and Telecommunications
• 2010.09 - 2014.07   Bachelor of Engineering, Computer Science Department, ShanDong University of Technology

---

Awards

• 2014.9-2017.3   The First Honor Graduate Scholarship for 3 consecutive years

---

Others

• I have been performing magic for nearly ten years. My favourite class of magic is card magic because it can be shown in almost any conditions like on desks or standing up. I had been president of magic club in my undergraduated college for 2 years and performed stage magic many times for the Welcome Party for the Freshmen. My favourite card magician is shin lim since his magic effects are so visual that like real magic and I also like his rhythm of performance, his choice of the background music and his emotion conveyed in his masterpiece. He is also the champion of FISM which is Olympic game in magic area. I also like cardistry, emerging in recent ten years, an finger activity using cards.