Hello!
I am an undergraduate student at Western Washington University in Bellingham, WA. I grew up in Seattle but my heritage is Catalan and Argentinian, and I am a speaker of both Catalan and Spanish. I enjoy making art , solving puzzles, and traveling. At WWU, I am studying Linguistics, Computer Science, and Math. I will graduate in June 2025 as the Outstanding Graduate in Linguistics with a BA in Linguistics and a BS in Mathematics/Computer Science. I am a student of the Honors College at WWU and I work as an upper-level math tutor on campus. I am also a part of Dr Brian Hutchinson's Machine Learning Research Group , Drs Jordan Sandoval and Kirsten Drickey's Spanish Language Learning Research Group, and Dr Maura O'Leary's Documentation, Analysis, and Revitalization in Linguistics Lab (DARLing). In Fall 2025 I will begin the Computational Linguistics Master's program at the University of Washington.
Projects
WWU Scholars Week 2024
I worked with a partner to conduct phonetic research in Catalan under the advisement of Dr Jordan Sandoval. Our poster was selected to be shown during Scholars Week and my partner and I presented our work to various people.
Alternations in Brazilian Portuguese
I independently researched phonological features in Brazilian Portuguese, using a grammar in addition to other resources and personal experience. I compiled my research into this paper , under advisement from Dr Jordan Sandoval.
Arbitrarily Deep Neural Network
Pair programming project where my partner and I implemented a NN from scratch, using numpy and argparse. The NN can train on classification and regression data, handles minibatching, and has an optional verbose mode. The user is able to input the data files, various hyperparameters, and other settings like problem type and report frequency. Based on the specified report frequency, the program evaluates the model on the dev set and prints the performance.
Phoneme Recognition Model
I used Scikit-learn's MLPClassifier to create an ensemble model of twelve NNs. Given a vector representation of audio, the model classifies that audio as one of 61 phonemes using probabilistic voting. The four best performing NNs are given more votes, increasing ensemble model performance. Details can be found in the report I wrote about this project.
Elizalike Chatbot
I added functionality to skeleton code of a chatbot so that the chatbot correctly uses regular expressions to handle personal deixis for all 1st and 2nd person subject pronouns, as well as all forms of the verb be. I also implemented keyword recognition in user input to prompt a predetermined response, or a response that retains a part of the input, depending on the keyword detected.
Menstrual Cycle Tracker
This program populates and displays a calendar with given and predicted data, allows the user to input new data, and calculates expected next period and average length of period and menstrual cycle. I created additional functionality so that the calendar displays the recorded daily symptoms and intensity as color and size coded dots, providing easily readable and accessible information to the user. The user is able to have full control over their medical information, ensuring privacy.
Zombie Videogame
I independently created a fully functioning zombie apocalypse themed text-based video game. It provides prompts and takes input from the user to determine the next stage of the game, with some randomization.
Blog Post
I independently did research on language technology for language revitalization and wrote this blog post on my findings. My goal was to investigate how language technology can help with language revitalization and what drawbacks it presents.
Sentence Annotation GUI
With advisement from Dr Sara Ng, I designed and implemented a GUI using tkinter that allows the user to annotate sentences. The idea behind this is to help with language revitalization. For low resource languages, synthetic data can be created in order for these languages to have a chance at benefiting from language technology. This GUI provides an easy way for native speakers to annotate synthetic sentences and saves their input so that linguists can use that information.
Research
Hutchinson Machine Learning Research Group
I'm part of a team that is working on a model to aid in the process of transcribing audio of toddler-adult interactions. We are collaborating with Dr Heather Moore from the Communication Sciences and Disorders department. In addition to my project, I attend weekly meetings, including a reading group, a tutorial given by a student in the group, and a status meeting where each team takes turns presenting on their progress.
Language Revitalization Lab
I am part of Dr Maura O'Leary's new lab, DARLing (Documentation, Analysis, and Revitalization in Linguistics), where I will help with revitalization efforts for the Athabaskan language Hän. I am working on the morphological transducer project, continuing the progress that has already been made, and will possibly collaborate with other researchers who are doing similar projects in related languages.
Language Learning Research
I've been working with Drs Jordan Sandoval and Kirsten Drickey to create a python script that will organize their data. The group has created a Qualtrics survey to collect information from students, and my script takes the excel file that Qualtrics produces and formats it in the way that the group needs. I am also working on a script that will create plots from the data based on user input. As my senior capstone for the Honors College, I will expand on this project and make my scripts interactive and user-friendly, likely through a GUI.
Contact
WWU email: centela@wwu.edu
Personal email: anukzc@gmail.com