About me
I am a 4th year undergraduate student at Johns Hopkins University. I major in Computer Science, Cognitive Science (linguistics focus), and Applied Mathematics (statistics focus). I'm intereted in using computational methods to model and potentially discover cognitive processes.
My research interests: Natural Language Processing, Multilingual/Cross-lingual NLP, Computational Sociolinguistics, Computational Soial Science, Low-Resource Machine Translation, Human-Centered NLP, Fair NLP
I have been working as a research assistant at the Center for Language and Speech Processing at Johns Hopkins University supervised by Philipp Koehn and Kenton Murray. I am in the process of applying to post-bac and PhD programs. Please contact me at sli136@jhu.edu if you are interested in my work!
Click here to view my CV (updated Jan. 23)
Current Projects
-
Robust L2 Translation
We develop a multilingual translation system from "broken" source sentences to investigate the differences between human language acquisition and machine language acquisition.
-
Mixture of Adaptors
We propose a parameter-efficient mixture of adaptor architecture for many-to-many machine translation, which is especially helpful for low-resource langauges.
-
Speech to Sign Language
We attempt to trian a diffusion model conditioned on speech signals to translate speech to animated ASL sign language.
News
-
12/20/2022
Check out our new paper "A Linguistically Motivated Study to Quantitatively Analyze Self-Supervised Speech Representations."
-
11/14/2022
Check out our new paper "Language Agnostic Code-Mixing Data Augmentation by Predicting Linguistic Patterns."
-
10/21/2022
Check out our new paper "A New Approach to Extract Fetal Electrocardiogram Using Affine Combination of Adaptive Filters."
-
10/07/2022
Check out our new paper "PQLM - Multilingual Decentralized Portable Quantum Language Model for Privacy Protection."
-
09/26/2022
Check out our new paper "End-to-End Lyrics Recognition with Self-supervised Learning."
-
07/09/2022
Check out our workshop paper "Genetic improvement in the shackleton framework for optimizing LLVM pass sequences" accepted to GECCO'22. Best Presentation Award
-
03/24/2022
Check out our paper "Optimizing LLVM Pass Sequences with Shackleton: A Linear Genetic Programming Framework" accepted to GECCO'22.
