Greetings

I'm a 4th-year Ph.D. candidate in Computer Science at the University of Toronto, working with Prof. Khai Truong in the DGP lab.

My research lies at the intersection of human–AI interaction, accessibility, and creativity support, with a special focus on improving music accessibility for d/Deaf and hard-of-hearing (DHH) individuals. My projects include song signing (CHI ’23) to explore how music is experienced and expressed within Deaf culture, and ELMI (CHI ’25), an LLM-supported English lyrics to ASL gloss translation system.

I completed my B.Sc. in Computer Science and Engineering at Ewha Womans University, where I was advised by Prof. Uran Oh (Human-Computer Interaction Lab) and Prof. Hyokyung Bahn (Distributed Computing and Operating Systems Lab).

Additionally, I worked as a research intern at Samsung AI Center Toronto, where I was mentored by Iqbal Mohomed, and at NAVER AI LAB under the supervision of Young-Ho Kim. Most recently, I interned at Adobe Research in the STORIE Lab, supervised by Anh Truong and Justin Salamon .

💼 I am currently exploring academic (Assistant Professor) and industry (Research Scientist) positions starting in Summer/Fall 2026.

Google Scholar | LinkedIn | suhyeon.yoo[at]mail.utoronto.ca

Labels

Artificial Intelligence: POS tagging & Word Embedding (Spring, 2020)

Class: Artificial Intelligence
Date: Spring 2020
Professor: Hyunsuk Park
Main Idea: POS Tagging with Decision Tree, Word Embedding
Methods: CBOW and SKIPGRAM
Results: 


First of all, I completed building an artificial neural network model using GENIA for POS tagging. POS tagging was applied to GnI papers using decision trees.

The frequency of each part-of-speech, the type of preceding word, etc. were identified and visualized in a word cloud, and used for chunking.

Next is “word embedding”. 1. Direct model design using tensorflow 2. Modeling using Word2Vec 3. Google model on the model created in the previous 2Modeling by crossing,

A total of 3 modeling methods were conducted.

Compared word vectors made of SKIP-Gram and CBOW.





라벨:

Comments

Post a Comment