![profile picture](https://dpl6hyzg28thp.cloudfront.net/media/bb76336c-c7a2-41ea-86d0-750bfdd96afa.jpg)
Celine L
- Research Program Mentor
PhD candidate at Cornell University
Expertise
natural language processing, machine learning, broadly engineering, audio processing, computational linguistics
Bio
Hi! My name is Celine, and I am a PhD candidate in computer science at Cornell University. I currently work on questions in natural language processing, especially how natural language processing techniques can make programming and software more accessible. My undergraduate degree background is in electrical engineering-- for my capstone project, I worked on selective audio filtering. Outside of the office, I like to spend my time being (1) active and (2) creative. (1) I play volleyball and frequent the gym and Ithaca's beautiful trails. (2) In my spare time, I pick up knitting, writing, embroidery projects, digital art doodles, and painters tape wall art.Project ideas
Could language models experience synesthesia?
Synesthesia is the experience in which some people (synesthetes) experience certain unrelated sensory or cognitive stimulation when experiencing another one. (For example, seeing colors when listening to music.) Word embedding models such as Word2Vec and GloVe are trained over large corpora of language to assign similar high-dimensional value vectors (word embeddings) to similar words. (For example, "apple" and "peach" would have more similar word embeddings than would "apple" and "swimming".) The goal of this project would be to determine whether these trained word embedding models might possess common synesthetic associations such as the letter A to the color red. How might these association, if any, vary across word embedding models trained on different languages?