Research Assistant – NLP for Singapore Mandarin Usage Dictionary

About the role

The School of Humanities at Nanyang Technological University seeks a full‑time Research Assistant to support the Singapore Mandarin Usage Dictionary project. You will work on corpus construction, speech‑to‑text processing, and the development of computational models that capture lexical variation in Singapore Mandarin.

Key responsibilities

• Support corpus construction, including speech‑to‑text processing and transcription of spoken data.
• Perform data preprocessing, cleaning, and quality checks on written and spoken corpora.
• Train, fine‑tune, and evaluate NLP models such as Word2Vec and BERT for lexical variation detection.
• Implement models and conduct systematic performance evaluations.
• Prepare model outputs for linguistic validation and integration into the dictionary.
• Contribute to the technical development of the online dictionary platform, including database integration and search functions.
• Document code, workflows, and datasets; assist with other project‑related tasks as assigned.

Required profile

• Bachelor’s degree in Computer Science, Computational Linguistics, NLP, or a related field.
• Hands‑on experience with NLP or machine‑learning model training, fine‑tuning, and evaluation.
• Proficiency in Mandarin Chinese to support project‑specific tasks.
• Strong written and oral communication skills and ability to work both independently and collaboratively.

Required skills

• Python programming.
• PyTorch and scikit‑learn libraries.
• Experience with Word2Vec and BERT models.
• Speech‑to‑text processing workflows.
• Familiarity with NLP toolkits and model evaluation techniques.