Natural Language Processing

Natural language processing (NLP) is a subfield of linguistics, computer science, information engineering, and artificial intelligence concerned with the interactions between computers and human (natural) languages, in particular how to program computers to process and analyze large amounts of natural language data. The ultimate objective of NLP is to read, decipher, understand, and make sense of the human languages. Our research focuses on representation learning, deep learning, and semi-supervised learning algorithms for various tasks in NLP.

Machine Commonsense refers to the ability of machines to make sound judgments and decisions based on everyday knowledge and experience. It involves understanding and applying basic concepts that are typically taken for granted, such as recognizing cause-and-effect relationships, interpreting social cues, and making assumptions about the physical world. Our research focuses on integrating this commonsense knowledge into language models by constructing benchmarks for commonsense reasoning, generating commonsense knowledge databases, and developing reasoning frameworks.

Korean NLP is a specialized field within computational linguistics focused on processing and analyzing the Korean language using machine learning, deep learning, and linguistic theories. The unique characteristics of Korean, such as its agglutinative structure, honorifics, and use of Hangul, present distinct challenges and opportunities for NLP. This introduction aims to provide a comprehensive overview of the fundamental concepts, tools, and applications of NLP techniques tailored to the Korean language. Our research focuses on constructing datasets that capture the unique aspects of Korean and developing methods that specialize deep learning models for Korean.