Summary
Overview
Work History
Education
Skills
Publications
Hobbies and Interests
Coursework
Certification
Timeline
Generic

Xinyi Liu

San Ramon,CA

Summary

NLP Developer with extensive experience at Montclair State University, specializing in training multilingual models and publishing research at ACL 2023. Proficient in Python and machine learning, with a strong focus on critical thinking and communication skills. Demonstrated ability to enhance project efficiency and deliver significant contributions to natural language processing.

Overview

3
3
years of professional experience
1
1
Certification

Work History

Graduate Assistant

Montclair State University NJ
Montclai, NJ
08.2023 - 05.2025
  • Trained multilingual transformer model (XLM-RoBERTa) to disambiguate euphemistic terms in diverse settings.
  • Collected over 3,000 Chinese euphemistic terms, organizing data with Google Sheets and Python libraries.
  • Collaborated on deep learning experiments, fine-tuning XLM-R-base and BERT-base models.
    Published findings at ACL 2023, demonstrating superior performance of multilingual models over monolingual counterparts.
  • Compiled idioms datasets spanning psycholinguistics and computational linguistics, identifying features across 50 datasets.
  • Partnered with ETS members to produce a research paper on idioms, currently under review.

NLP Developer Volunteer

Linguistic Justice League
05.2022 - 09.2022
  • Collaborated with project managers, designers, and developers to enhance task completion efficiency.
  • Developed a book translation program to convert English text into low-resource languages like Hindi, Arabic, and Telugu.
  • Analyzed code to identify and rectify errors, optimizing overall output.

Education

Master of Science - Computational Linguistics

MONTCLAIR STATE UNIVERSITY
Montclair, NJ
05.2025

Bachelor of Arts - Linguistics, Computer Science

RUTGERS, THE STATE UNIVERSITY OF NEW JERSEY
New Brunswick, NJ
05.2023

Skills

  • Natural language processing
  • Machine learning
  • Critical thinking
  • Effective communication
  • Programming in Python (Matplotlib, TensorFlow, PyTorch, scikit-learn, NLTK)

Publications

MEDs for PETs: Multilingual Euphemism Disambiguation for Potentially Euphemistic Terms, Patrick Lee, Alain Chirino Trujillo, Diana Cuevas Plancarte, Olumide Ojo, Xinyi Liu, Iyanuoluwa Shode, Yuan Zhao, Anna Feldman, Jing Peng, 2024, Findings of the Association for Computational Linguistics: EACL 2024, St. Julian's, Malta, 875-881

Hobbies and Interests

  • Traveling
  • Hiking
  • Photography

Coursework

  • Computational Linguistics
  • Quantitative Linguistics
  • Statistics and Probabilities
  • Python Programming
  • Special Topics in Natural Language Processing
  • Text Analysis Tools (Linux)
  • Machine Learning

Certification

  • NLPNatural language processing with Python (udemy)
  • SQL for data science (coursera)
  • Using python to access web data (coursera)

Timeline

Graduate Assistant

Montclair State University NJ
08.2023 - 05.2025

NLP Developer Volunteer

Linguistic Justice League
05.2022 - 09.2022

Master of Science - Computational Linguistics

MONTCLAIR STATE UNIVERSITY

Bachelor of Arts - Linguistics, Computer Science

RUTGERS, THE STATE UNIVERSITY OF NEW JERSEY