Skip to content

chengxuan-xia/chengxuan-xia.github.io

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

61 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

About Me

I am a graduate student with over 2 years of industry experience in AI, and over 2 years of academic research experience in Computer Science.

My passion for programming and applying advanced tech to the real world drove me to change my major from Physics to Computer Science and now pushes me to continue my study and develop my future career in Computer Science & Natural Language Processing in Silicon Valley.

As a future professional in software engineering, I specialize in both front-end and back-end, equipped with knowledge in the area of Machine Learning and Natural Language Processing. Now, I am looking to utilize my programming skills and make our life better with my effort.


Education Background

Sept. 2022 - Mar. 2024 University of California, Santa Cruz

  • M.S in Natural Language Processing
  • GPA:3.9/4.0

Sept. 2019 - Jun. 2022 University of Chinese Academy of Sciences (UCAS)

  • M.S in Computer Science

Sept. 2014 - Jun. 2019 UCAS

  • B.S in Physics

Professional Experiences

Sep. 2020 - Jul. 2022 Beijing Paoding Technology LTD

Software Development Engineer, Research Department

Fullstack Web Development with ML Backend

  • Trained a weak-supervised model for keyword-based label generator
  • Generated 6 million high-quality labeled data, (equivalent to 6 months’ work and cost of $20,000 from human annotation
  • Developed a user-friendly web UI tool using TypeScript, CSS, and HTML
  • Implemented an application with Flask API to extract and match the value-description pairs from financial statements, with SQLite Database
  • The application was productized and sold to 16 audit firms, on average reducing 30 hours manual work per month

Language application for unstructured documents

  • Built a Python library for data processing, information extraction from over 60k sentences documents with REST APIs for downstream usage
  • Constructed a bi-directional LSTM RNN model to accurately identify and extract elements such as tables, paragraphs, and pictures from unstructured documents such as contracts and financial statement

Sep. 2020 - Jan. 2021 UCAS

Undergraduate Teaching Assistant

  • B0911012Y Foundations of Artificial Intelligence

Research Experiences

Jul. 2020 - Jun. 2021 Key Lab of Intelligent Information Processing, CAS Research Assistant

Full Stack: E-Commerce Website application

  • Built a full-stack E-commerce website with Angular front-end and Java Spring Boot back-end
  • Utilized advanced development tools such as IntelliJ, Visual Studio Code to develop the code for the product catalog, shopping cart and checkout

Logical Relation-based Textual Similarity Searching

  • Built a classification model with 12 embedding layers, a bi-LSTM as transformer, and combined with a financial KG and context message as external knowledge. It extract 4 logical relations in financial texts and expand the scope of application of traditional Semantic Textual Similarity tasks; achieved 0.963 F1 score
  • Upgraded an algorithm for a Named-Entity Recognition task that extracted structured information. Improved the system’s accuracy from 0.92 to 0.96

Nov. 2019 - Jan. 2020 CCF Big Data & Computing Intelligence Contest

  • Built a machine learning model based on BERT to analyze emotional preference of Internet news, achieved 0.817 accuracy, among top 2% of all competitors

Leadership Activities

Sep. 2019 - Sep. 2020 Editorial Department, UCAS | Production editor

  • Led a team of 30 to produce daily publications on the official accounts of UCAS on WeChat (with over 230k followers), including managing writers and other publishing staff, editing content, and approving final layouts

Jul. 2015 Greenway International Teaching Volunteer Program

  • Led volunteers from different nations to instruct English to 40 local students with self-designed syllabus and teaching methods

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages