Natural Language Processing

Natural Language Processing (NLP) is a field of artificial intelligence that enables computers to understand, interpret, and learn patterns from human language. By identifying meaningful structures in human language NLP models can generate language, predict information, and analyze linguistic data. These capabilities support a wide range of applications, including translation, question answering, text generation, sentiment analysis, and information extraction.

Our research focuses on adapting and specializing NLP models for specific domains, including scientific literature, clinical records, and culture/domain-specific language models. Our overarching goal is that supporting people to understand each other regardless of their domain or cultural differences via lens of technology.

Nature Language Processing
(Bioinformatics)

Bioinformatics is an interdisciplinary field that uses computational methods to understand and analyze the language of nature encoded in DNA, RNA, and protein sequences. By learning meaningful patterns and relationships within biological sequences, computational models can reveal how genetic information is organized and how it contributes to biological functions and processes. These models support a wide range of tasks, including predicting the functions of genes/proteins, identifying genomic signatures (DNA fingerprinting), and predicting protein–protein interactions.

Our research focuses on developing and applying machine learning and LLM-based approaches to biological sequence analysis. We aim to build models that can learn complex biological patterns and use them to generate meaningful predictions and insights into genes, proteins, and their interactions. Our overarching goal is to contribute to human health by understanding and harnessing the language of life.