Projects
Arranged by Time
iOS DMV Test Practice
Application for Chinese in America to do practice on DMV driver license test
Relationship Conceptualization
As numbers of high-quality, large volume knowledge graphs appear, information extraction work has been enriched with more semantic knowledge. However, the entity relation extraction based on the knowledge graph is still at a very intuitive early stage, and the key issue it faces is the relation recognition and classification. Current works are mostly based on manually constructed entity ontology, where coarse-grained entity types are fixed for syntactic analysis on classification or clustering on detecting new relations. In order to break the shackles of ontology and describe the relationship between the entities with fine-grained types, we propose a two-step bottom-up abstraction approach for relation conceptualization based on conceptual taxonomy that is automatically constructed. Given an entity relation, we figure out a group of Top-K concept pairs to abstract the relation, according to the typicality, diversity and coverage features. Our experimental evaluation shows that our method performing significantly high precision and quality for detecting fine-grained relationships.
This project is my undergraduate thesis with prof.Yanghua Xiao.
Download Slides / Download Thesis Paper (Chinese)
CNELL
One project of Knowledge Works which extracts Chinese relationships from thousands of news pages. (The website will be maintained in the future on my page)
GitHub: CNELL
Relationships [relation](entity1, entity2) are extracted from the website url after the relation.
Knowledge Works
Knowledge Works is the website of GDM lab of Fudan University, under Key Laboratory of Data Science in Shanghai. The website is currently continuously building by students. My responsibility was to design and implement the prototype of the website.
Knowledge Works
Drawear
This is an iOS application of my course project which allows user draw graph, upload image to the design their own T-shirt. The application won the Second Runner-up of 8th Shamrock Software Competition.
Teammates: Wenqi He (University of Illinois at Urbana-Champaign), Cheng Qian (Fudan University), Xuhua Xia.
GitHub: Drawear
Word Master
Recite English Words Application. This is a simple project of Software Engineering Course. My teammates and I designed and implemented a Java based application for Chinese student to recite English words. The application has reciting function with many options and statistic data.
Teammates: Wenqi He (University of Illinois at Urbana-Champaign), Cheng Qian (Fudan University), Ye Zhang (Tencent)
Download
