Research Field : Natural Language Processing
Natural Language Processing is a technique to create a form that can be understood by computers and mechanical analysis of human language. It is divided into detailed morphological analysis, part-of-speech attached, verses unit analysis, and syntax analysis. Natural Language Processing use technology such as search engine, interpreter, voice recognition, artificial intelligence, which are utilized in various fields.
Research Field : Artificial Intelligence
Artificial intelligence (AI) is intelligence exhibited by machines or software. It is also the name of the academic field of study that studies how to create computer software capable of intelligent behavior. The general problem of simulating (or creating) intelligence has been broken down into a number of specific sub-problems. The central problems (or goals) of AI research include reasoning, knowledge, planning, machine learning, affective computing, natural language processing, information retrieval, perception, and the ability to move and manipulate objects.
We have studied subfields and conducted various projects to solve several technical issues for AI.
Our specific research for AI includes the following.
– Opinion Mining with a Syntactic Structure Analyzer in natural language processing
– Language Typewriter for Brain-Computer Interface in BCI
– Computer Aided Language Learning for diagnosis of recognition
– Mind Wandering Judgment System using information retrieval technology and machine learning technology
– Extraction of User Intention from Web Search Logs in information retrieval
We have also developed various solutions utilizing our research.
– Corpus Information Retrieval
– Document Classifier
– Morphological Analyzer
– Automatic Spacing Proofreading using natural language processing technology
– Cognitive Enhancement Games
– Brain HIT
– Korean IME with BCI using brain-neuro science and recognition science
You can experience this research firsthand using the demo systems under the Research menu.
Research Field : Machine Learning
Machine learning was developed to solve complex problems, which to this day have not been perfectly solved, such as pattern recognition, automatic translation, and semantic role labeling. Techniques such as Support Vector Machines, Hidden Markov Models, and Neural Networks are used depending on the type of problem and over large data sets exhibit benefits over traditional models. Whereas traditional models are often overwhelmed by large amounts of data, newer techniques thrive on it. Our lab investigates deep learning techniques to extract features out of large amounts of data and train models to recognize and classify unseen pieces of data.
Research Field : Deep Learning
Neural networks, a type of machine learning, have only recently become practical due to new training techniques and the ability to execute quickly on the GPU, and our lab is investigating how to use neural networks to process text like the human brain. Typically, deep learning techniques such as convolutional neural networks are used for pattern recognition. However, due to the fact that neural networks traditionally accept a fixed set of inputs, new types of models such as recurrent and recursive neural networks are gaining traction because they can accept sequences. Very recently, these new sequence-processing neural network models have surpassed traditional models in various text-related tasks such as sentiment analysis and semantic role labeling. We hope to push the boundaries of these algorithms and develop hybrid solutions that maximize effectiveness by combining traditional techniques with state-of-the-art deep learning models.
Research Field : Learning Analytics
Recently, interest in how this data can be used to improve teaching and learning has also seenunprecedented growth and the emergence of the field of learning analytics. In other fields,analytics tools already enable the statistical evaluation of rich data sources and the identification of patterns within the data. These patterns are then used to better predict future events and makeinformed decisions aimed at improving outcomes
Learning analytics is the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimising learning and the environments in which it occurs.
The definition and aims of Learning Analytics are contested. One earlier definition discussed by the community suggested that Learning analytics is the use of intelligent data, learner-produced data, and analysis models to discover information and social connections for predicting and advising people’s learning.”
Research Field : Educational Data Mining & Artificial Intelligence in Education
Educational Data Mining(EDM) and Artificial Intelligence in Education(AIED) describes a research field concerned with the application of data mining, artificial intelligence, machine learning and statistics to information generated from educational settings. These studies develop student model, expert system, learning management system and intelligent tutoring system to support students and improve motivation, achievement, attention for effective learning. The goals of these fields are predicting, discovering, studying, advancing. The predicting is to predict student’s future learning behavior with user experience and satisfaction of the learner.
The discovering is to discover new and improvement models. For example, mooc(Massive open online course) is a new model for effective learning based on collaborative and SNS. The studying is to study the effects of educational support that can be achieved through learning systems. The Advancing is to advance scientific knowledge about learning and learners by building and incorporating student models, the field of EDM research and the technology and software used. Our research object is to achieve these goals for effective and efficient learning.
Research Field : Information Retrieval
Search and browse the information that user require and provide the technology to find the information. It is widely used in Google and NAVER, such as Web search engines. The search engine helps user with software to help them find data easily among a lot of data and give user the information they need from the Internet. The search results will vary depending on the search criteria. It depends on how search engines search the topic, meta search, word search, and many other kinds of knowledge search.