Claire (Zhiyue) Liu

Software Developer
eyre.lzy@gmail.com

Zhiyue (Claire) Liu | Portfolio
 

A 2-year CMU CS master,

Experienced in scrum software development,

Passionate in backend data-driven problems, resolving ambiguities, taking challenges and making contribution.

Looking for FULL-TIME position in 2016.

Feel free to view my Resume, visit my Github, and Linkedin, and to endorse my skills.

  • Java
  • Python
  • C#, ASP.NET
  • SQL
  • NoSQL
  • JSP
  • CSS, HTML5
  • C, C++
  • JavaScript
  • Matlab
  • Information Retrieval
  • Machine Learning
  • Struts-Spring-Hibernate
  • BootStrap
  • Data Mining
  • Big Data(Hadoop)
  • Flask
  • UIMA
  • Maven
  • Eclipse
  • Visual Studio
  • MySQL
  • mongoDB
  • Git
  • StarUML

Education & Course.

Courses:

  • Search Engine (11642) (A+)
  • Design and Engineering of Intelligent Information System (11791) (A+)
  • Advanced Data Structure and Algorithm (02613) (A)
  • Machine Learning (11601) (A)
  • Big Data in Practice (11653)(A-)
  • Cloud Computing (15619)
  • Robotics & Machine Learning (02750)
Expected Graduation Date: May 2016
Major: Master of Science in Language Technology Institute, School of Computer Science
QPA: 3.96/4
Place: Pittsburgh, PA

Courses:

  • Object-Oriented Programming
  • Database
  • Data Structure & Algorithm
  • Software Engineering
  • Machine Learning
  • Intelligent Retrieval System
  • Compilation
Date: Sep, 2011 - June, 2015
Major: Bachelor of Science in Software Engineering
GPA: 93.5/100
Rank: 1/27
Place: Harbin,China
Publication: Mining social web(2nd) interpreted in Chinese
Honor: National Scholarship (top 1)

Work.

 
 
  • HRMS
  • HRMS
  • HRMS
  • HRMS

Summer Intern - Human Resource System

Overview:

Led 5 other interns, built a website based on Struts-Hibernate-Spring (SSH) framework, and utilized project management tools like Git for collaborated work.

My Contribution:

  • User Interface Design
  • Developed core module for recruitment
  • Applied BootStrap for user interface
  • Designed database schema
  • Performed unit and integration testing
Date: Aug 2013
Client: CS&S
Place: HIT
See its details
 
  • Amazon Echo
  • FireTv

Amazon SDE intern

Overview:

After all tokens are labeled, NLU(natural language understanding) then transforms the raw text into structured data, including info like utterance's intent, and its details(we called it Slot). For example, play music intent has slots like song name, artist name, and etc. Slots need to be resolved into entities by searching in remote indexes. My project provides configurable catalog policies for resolution. After my changes, any client could add his customized catalog policies based on his need, and they could help him enhance both search speed and accuracy.

My Contribution:
  • Keep current functionality, and in the meantime, simplify the logic, centralize and externalize configurations into json policy file
  • Make policies extendible for future use cases, and configurable by all our clients like echo, firetv etc.
  • Add new features, to support functionality of i) resolving different slots by different catalogs ii) resolving slots conditioned on other information
Date: May, 2015 - Aug, 2015
See the product
 
  • TA for 2015 Fall Search Engine
  • TA for 2015 Fall Search Engine

TA for 2015 Fall Search Engine

Overview:

I'm TAing course 11642: Search Engine(Jamie Callan) for Fall 2015 semester. I'm responsible for office hours, grading, design of homework and exam.

My Contribution:

  • Office hour
  • Grading
  • Design of homework and exam
  • Tutoring
Date: Sep, 2015 - now
Course website
 
Human Resource Management System HIT SUMMER INTERN: Human Resource Management System
Amazon SDE intern Amazon's SDE intern in NLU Engine Team, for Amazon Echo, FireTv, and etc.
CMU TA for 2015 Fall Search Engine CMU TA for 2015 Fall Search Engine

Projects.

Large Scale Distributed Search Engines

My Contribution:

  • Supported query operators
  • Implemented retrieval models/algorithms
  • Reformed queries with Sequential Dependency Model, pseudo relevance feedback
  • Reranked with SVM for Learning-to-Rank Algorithm

Overview:

Designed and implemented a text-based large scale search engine indexed with Lucene API on corpus of 500,000+ documents from ClueWeb09 dataset Evaluated by metrics like MAP and NDCG. Supported query operators(like NEAR, WINDOW, WSUM) and retrieval models including Ranked Boolean, BM25, Indri and etc. Applied Sequential Dependency Model, pseudo relevance feedback to expand queries and improve performance. Adopted SVM for Learning-to-Rank Algorithm to improve document reranking.

Date: Jan-May 2015
Tag: CMU Course Project

Biomedical Question Answering System

My Contribution:

  • Query Processing & Combining
  • Pipeline Construction
  • Error Analysis
  • System evaluation & improvement
  • Exact Answer Generation
Visit its code See its video

Overview:

With 3 members, built a BioASQ system among PubMed articles aiming at automatically answer biomedical "yesno" questions, using UIMA framework and third party tools like OpenNLP, Lucene.

Designed system pipelines, including questions generating, document retrieval and then re-ranking, and extract exact answer.

Date: Nov-Dec 2014
Tag: CMU Course Project

TravelGene

My Contribution:

  • Front-end architecture design
  • profile page design
  • calendar page design
Visit its code See its video

Overview:

We're building a travel tool to disrupt the traditional way of organizing a trip when we have to spend a lot of time on searching from various websites for the flight tickets, hotels and places to visit, collecting information, and comparing the results to make final decision. With our tool, you can get rid of all these troubles. With just a few clicks, your interest, profiles will be taken into consideration to make reasonable recommendation due to our real-time machine learning techniques.

Date: Sep 2014-Now
Tag: TWO-YEAR CMU Entrepreneurial Project

Efficiency Management Win8 App(Ranked 1st)

My Contribution:

  • Team Management
  • Designed a pseudo 3D navigator UI in metro-style
  • implemented interface to access JSON data
  • Realized features like system alert, live titles, personalized templates
Visit its code

Overview:

This is a to-do list app on Win8 platform implemented by HTML5, JavaScript, JSON. We have a fancy 3D interface, to see all the functional panels. Here, we could add a thing to do with our system task template. You could also build your own template. With this tool, we could manage your daily tasks in an easy way. This could also be used in tablets and cell phones, and use gestures to operate on these devices.

Date: Jul 2013—Jul 2013
Tag: HIT Course Group Project

Mining Closed Relationship among Classmates

My Contribution:

  • Cleaned call log data
  • Implemented K-means to cluster closed classmates
  • Visualized the results as a social network graph using C#
  • Introduced heuristic rules to improve model’s performance by 11%(measured by f-score)
Visit its code

Overview:

Aimed to see close relationship among my classmates by analyzing and extracting useful features from their call record data. Applied k-means, where k=2, to group contacts in each call record into clusters.
Obtained both labeled training and test data from classmates under professor's support. Finally, visualized the relationship result with graph whose edges are represented by the relation score of every two nodes.

Date: May, 2014
Tag: HIT Course Project

Light Self Blog

My Contribution:

  • Applied HTML/CSS into front-end
  • Built page templates
  • Developed J2EE Architecture
  • Coding & Reconstruction
  • Testing
Visit its code

Overview:

This is a website for users to write and share their blogs. Users could view and post articles and also write comments. Top hot articles are listed on the homepage.

Date: Jun, 2014
Tag: HIT Course Project

Feature Extraction for Effective Content-based Cloth Image Retrieval in E-Commerce

My Contribution:

  • Color feature analysis
  • Color feature extraction
  • Data crawling

Overview:

It's a group project on Content-based Cloth Image Retrieval by crawling 20000+ Amazon’s women clothes.
Currently, clothes are searched by text-content. What if we see some fancy clothes in department store and what to search on Amazon? In our project, we could upload an image and search clothes by it. Also, we have a better performance to search clothes in specific color group.

Date: April, 2014
Tag: HIT studio's Group Project

Curriculum Schedule Android App

My Contribution:

  • App design and implementation
Visit its code

Overview:

This is an android app to schedule daily courses. After importing your courses, you could view them anytime and anywhere.

Date: April, 2013
Tag: HIT Course Project

Game Pu Pu Producer

My Contribution:

  • HTML/CSS
  • Front-end Design
Visit its code Visit its video

Overview:

Collaborated with 3 teammates, designed a strategic game aimed to help people with healthy diets using HTML5, jQuery and etc. Obtained the Best Participation Award, Imagine Cup, Microsoft’s Global Student Technology Competition (2013).

Date: Dec, 2013
Tag: Imagine Cup's HTML5 Game Competition

Contact.

Get in touch:

@Copyright 2015 |Developed by Zhiyue Liu

 5506 Fifth Ave Apt #303A, Pitts, PA
 412-953-6504
zhiyuel@andrew.cmu.edu
eyre.lzy@gmail.com