
Software Engineer
Amazon
Jun '20 - Present
I am a software engineer at Amazon after pursuing my master degree in Computer Science at University of Southern California. Previously, I am lucky to have opportunities to work with Dr. Thomas Couronné as a data scientist intern at AirAsia, and Dr. Wei-Yun Ma as a research assistant at Chinese Knowledge and Information Processing Lab (CKIP Lab), Institute of Information Science, Academia Sinica. I received my Bechalor's Degree in Computer Science at National Tsing Hua University.
Software Engineer
Amazon
Jun '20 - Present
Data Scientist Intern
AirAsia
Jun '19 - Aug '19
Research Assistant
CKIP Lab, Academia Sinica
Aug '16 - Jun '18
Software Engineer Intern
IBM
Jun '15 - Aug '15
M.Sc in CS
USC
Aug '18 - May '20
B.Sc in CS
NTHU
Jun '12 - Aug '16
Employed Transfer Learning using ELMo embeddings for sentiment analysis on customer feedbacks. Achieved 85% accuracy which is a superior performance with Google AutoML NLP API. Saved the model prediction cost for approximate $12,000 USD annually comparing to Google AutoML API.
Designed a distant supervision model applying noisy labeling using PyTorch. This work mainly focus on cosmetics domain and most cosmetic entities are offered from PIXNET StyleMe.
Proposed an algorithm to improve word embedding on presenting Wikipedia titles in Python and also improved spearman correlation score on word similarity task by 10%.
Created large evaluation benchmarks for Chinese word embeddings in both word similariy task and analogical reasoning task by manually translating from English benchmarks.
Designed a simulated intelligent program able to answer simple WH-questions and make sentences with given words in Java which can achieved around 90% of correction rate. Also, built the knowledge base for this program by SQLite.
Developed a real-time traffic signal detection algorithm for drivers as an Andriod app. In order to achieve real-time performance on Android devices, system is optimised to cope with 20 fps.
Developed a two-player game inspired by Flappy Bird and implemented on FPGA board in Verilog. Also, connected the FPGA boards with wires that enables the game to display simultaneously on both screens.
Designed a gamification program that can categorise people's photos in Java. Also, constracted an interface that can easily demenstrate each person's photos from database.
LREC 2020 [Paper]
LREC 2018 [Paper]
IALP 2017 [Paper]
Best Paper Award