Contrastive Learning of Sentence Representations

A novel approach which applies contrastive learning to learn universal sentence representations on top of pre-trained language models.

SteLLA: A Structured Grading System Using LLMs with RAG

A structured automated grading and feedback system which applies LLMs with RAG techniques.

Representation Learning of Connotation and Denotation Knowledge for Atomic Information Units

A project to investigate how to represent a word with an internal structure (e.g., a neural network) beyond the existing approach of vector space to support more sophisticated symbolic processing techniques beyond shallow string matching.