Natural+Language+Processing
-
Sungjoon Park Named Google PhD Fellow
PhD candidate Sungjoon Park from the School of Computing was named a 2019 Google PhD Fellow in the field of natural language processing. The Google PhD fellowship program has recognized and supported outstanding graduate students in computer science and related fields since 2009. Park is one of three Korean students chosen as the recipients of Google Fellowships this year. A total of 54 students across the world in 12 fields were awarded this fellowship.
Park’s research on computational psychotherapy using natural language processing (NLP) powered by machine learning earned him this year’s fellowship. He presented of learning distributed representations in Korean and their interpretations during the 2017 Annual Conference of the Association for Computational Linguistics and the 2018 Conference on Empirical Methods in Natural Language Processing. He also applied machine learning-based natural language processing into computational psychotherapy so that a trained machine learning model could categorize client's verbal responses in a counseling dialogue. This was presented at the Annual Conference of the North American Chapter of the Association for Computational Linguistics.
More recently, he has been developing on neural response generation model and the prediction and extraction of complex emotion in text, and computational psychotherapy applications.
2019.09.17 View 6951 -
Successful Development of Excavation System of Biomarkers containing Protein Decomposition Control Enzyme Information
A Korean team of researchers successfully developed a biomarker excavation system named E3Net that excavates biomarkers containing information of the enzymes that control the decomposition of proteins. The development of the system paved the possibility of development of new high quality biomarkers.
*Biomarker: Molecular information of unique patterns derived from genes and proteins that allow the monitoring of physical changes from genetic or environmental causes.
Professor Lee Kwan Soo’s team (Department of Biological Sciences) composed of Doctorate candidate Han Young Woong, Lee Ho Dong Ph.D. and Professor Park Jong Chul published a dissertation in the April edition of Molecular and Cellular Proteomics. (Dissertation Title: A system for exploring E3-mediated regulatory networks of cellular functions).
Professor Lee’s team compiled all available information of the enzyme that controls protein decomposition (E3 enzyme) and successfully compiled the inter-substrate network by extracting information from 20,000 biology related data base dissertations. The result was the development of the E3Net system that analyzes the related cell function and disease.
Cells have a system that produces, destroys, and recycles proteins in response to the ever changing environmental conditions. Error in these processes leads to disease.
Therefore finding the relationship between E3 enzymes that control the decomposition of proteins and the substrates will allow disease curing and prevention to become much easier. E3 enzyme is responsible for 80% of the protein decomposition and is therefore predicted to be related to various diseases.
However the information on E3 enzyme and inter-substrate behavior are spread out among numerous dissertations and data bases which prevented methodological analysis of the role of the related cells and characteristics of the disease itself.
Professor Lee’s team was successful in creating the E3Net that compiled 2,201 pieces of E3 substrate information, 4,896 pieces of substrate information, and 1,671 pieces of inter-substrate relationship information. This compilation allows for the systematic analysis of cells and diseases.
The newly created network is 10 times larger than the existing network and is the first case where it is possible to accurately find the cell function and related diseases.
It is anticipated that the use of the E3Net will allow the excavation of new biomarkers for the development of personalized drug systems.
The research team applied the E3Net to find tens of new candidate biomarkers related to the major modern diseases like diabetes and cancer.
2012.05.30 View 11726