Sydney Greenspun - Computational Linguist

Hello, I'm Sydney Greenspun

Computational Linguist bridging language and technology

Learn More

About Me

I'm a Computational Linguist passionate about using Natural Language Processing (NLP) to support linguistically marginalized communities. Growing up in the linguistically diverse Los Angeles area inspired my interest in language, while computational linguistics introduced me to computer science. I have combined these interests through internships in NLP, localization, and frontend development, with experience in machine translation, OCR for Indigenous languages, and machine learning. I hold a B.A. in Linguistics and a M.S. in Human Language Technology from the University of Arizona.

My Skills

Here's a breakdown of the technical skills and tools I've acquired throughout my journey.

Programming & Scripting

  • Python NumPy, Pandas, Scikit-learn, TensorFlow
  • JavaScript Vanilla, DOM Manipulation
  • SQL Database Queries, Data Manipulation

Web Technologies

  • HTML5 Semantic Structure
  • CSS3 Flexbox, Grid, Responsive Design
  • Version Control Git, GitHub

Data & ML

  • Analysis Excel, Tableau
  • NLP Preprocessing, Training
  • ML Classify, Regress, Cluster

Tools & Platforms

  • IDEs VS Code, Jupyter Notebooks
  • Cloud Platforms
  • Project Management

Experience

Highlights of my professional journey and the roles I've held.

NLP Intern (2024-2026)

  • Led a team of five undergraduate researchers on NLP and language technology projects
  • Trained and evaluated custom Optical Character Recognition (OCR) models for Indigenous languages
  • Collaborated using GitHub for version control and project management

Front End Intern (Summer 2025)

LetzChat

  • Built a website integrating and customizing LetzChat’s patented machine translation program
  • Developed own machine translation website using Google API and JavaScript

Disability Technology (Summer 2025)

Digital Cinema Distribution Coalition

  • Conducted research on accessibility technologies used in cinema for individuals with hearing and visual impairments
  • Prepared reports and presentations for prospective investors and stakeholders

Localization Intern (Summer 2024)

  • Collaborated with a global team to localize media content for various international markets, ensuring cultural and linguistic accuracy.
  • Presenting complex AI data to clients using Excel and Powerpoint
  • Utilized internal tools and platforms like Tableau to track project progress, metrics, and bench marks.

Projects

OCR

Custom OCR Model

#neuralnetworks #NLP

Customized a Tesseract Optical Character Recognition model to digitize old scanned books for an Indigenous tribe.

  • Text generation and image creation
  • Leadership
  • LSTM based model and training
  • Achieved 5.5% Character Error Rate
Link to Project
Languages

Language Detection

#NLP #pre-processing-text

A model that predicts the language of inputted text based on data of over ten languages.

  • Tokenization and text pre-processing
  • Multinomial Naive Bayes model and vectors
  • 96% accuracy on testing data
Link to Project
Website

This Website

#HTML #CSS #Webdesign

This website was created with the help of LetzChat and consulting with W3Schools and AI

  • HTML5
  • CSS3
  • JavaScript
Link to Project Read Me
Translate

Ground-Up Translator

#API #JavaScript

Built my own website translator using Google Cloud Translate API. Along with that, it has features to do not translate certain words and to detect languages

  • Google Cloud API
  • REST API
  • Javascript
Link to Project Read Me
Languages

Language Wiki

#Python #SQL #Software Program

Created an interactive webpage that allows users to search and learn about languages

  • Ethical webscraping and SQL database implementations
  • Use of Docker, DB management programs, thorough testing
  • Python, JavaScript, HTML, Flask API
Link to Project
Authorship

1st Place in Text Classification Competition

#Transformers #NLP

Identified authorship with 68% accuracy (top of my class)

  • Pandas and Dataframe integration
  • HuggingFace Seq2Seq transformer
Link to Project

Contact

I'd love to connect! Feel free to reach out via the methods below.

Contact Form