Publications
2022
- Deep learning for patent landscaping using transformer and graph embeddingTechnological Forecasting and Social Change
2021
- KLUE: Korean Language Understanding EvaluationAdvances in Neural Information Processing Systems 34 (NeurIPS), May 2021.
- Unsupervised neural machine translation for low-resource domains via meta-learningAnnual Meeting of the Association for Computational Linguistics (ACL) (Oral), Aug 2021.
2020
- PATQUEST: Papago translation quality estimationProceedings of the Fifth Conference on Machine Translation (WMT)
- A multilingual neural machine translation model for biomedical data1st Workshop on NLP for COVID-19 (Emergency workshop at EMNLP), Dec 2020.
- Hybrid machine learning approach for popularity prediction of newly released contents of online video streaming servicesTechnological Forecasting and Social Change, Dec 2020.
- Revisiting round-trip translation for quality estimationProceedings of the 23rd Annual Conference of the European Association for Machine Translation (EAMT), Nov 2020.
- A context-aware citation recommendation model with BERT and graph convolutional networksScientometrics, Jul 2020.
- Patent document clustering with deep embeddingsScientometrics, Mar 2020.
- Text classification using capsulesNeurocomputing, Feb 2020.
2019
- Supervised Paragraph Vector: Distributed representations of words, documents and class labelsIEEE Access, Feb 2019.
- 어체 변환이 가능한 기계 번역 방법 및 시스템KR Patent Application, Jan 2019.
2018
- Stock price prediction through sentiment analysis of corporate disclosures using distributed representationIntelligent Data Analysis Journal, Dec 2018.
2017
- N3WS: Interactive newspaper article navigation via keyword and summary Extraction한국정보처리학회 추계학술발표대회, Nov 2017.
- This work was done as a result of the Hanium undergraduate mentoring project.
2016
- 밑바닥부터 시작하는 데이터 과학: 데이터 분석을 위한 파이썬 프로그래밍과 수학, 통계 기초도서출판 인사이트, Jun 2016.
- Korean translation of Data Science from Scratch: First Principles with Python by Joel Grus.
- Automated discovery of construction tacit knowledge based on text mining: A Preliminary studyCIB World Building Congress, Tampere, Finland, May 2016.
2015
- D3를 이용한 시각적 스토리텔링, 도서출판 인사이트, Jun 2015.
- Korean translation of Visual Storytelling with D3: An Introduction to Data Visualization in JavaScript by Ritchie King.
- Pseudo term vector representation for fast document clustering (of Korean text)Korean Institute of Industrial Engineering Spring Conference, Jeju, Korea, Apr 2015.
- 한국어 뉴스 기사에서 바이그램을 활용한 온라인 토픽 탐지 (Using bigrams for online topic detection in Korean news articles)Domestic conference on Korean Institute of Information Scientists and Engineers, Jeju, Korea, June 2015.
- 북한 신년사에 대한 자동화된 텍스트 분석: 1946-2015 (Text analysis of North Korean New Year addresses: 1946-2015Korean Political Science Review, 49.2, pp. 27-61, Feb 2015.
2014
- 한국어 형태소 분석기의 현황 및 특성 비교 (Survey and comparison of Korean open source morphological analyzers)Korea BI Data Mining Society (KDMS) Fall Conference, Nov 29 2014.
- 웹기반 한국어 워드클라우드 생성기의 개발 및 활용 (The development and application of a Web-based Korean wordcloud generator)Korea BI Data Mining Society (KDMS) Fall Conference, Nov 29 2014.
- KoNLPy: 쉽고 간결한 한국어 정보처리 파이썬 패키지 (Korean natural language processing in Python)Proceedings of the 26th Annual Conference on Human & Cognitive Language Technology, Chuncheon, Korea, 2014.
- KoNLPy (pronounced “ko en el PIE”) is a Python package for natural language processing (NLP) of the Korean language. KoNLPy was a pet project I’ve done during my Ph.D. studies at Seoul National University, in order to lower the barriers of Korean NLP.
- Bridging the semantic gap in multimedia retrieval with topic extraction from user reviews searchINFORMS Big Data Conference. San Jose, United States, 2014.
- Data based segmentation and summarization for sensor data in semiconductor manufacturingExpert Systems with Applications 41.6, pp. 2619-2629, 2014.
- Apparatus and method of segmenting sensor data output from a semiconductor manufacturing facilityUS Patent (Grant US9696717B2). Pending in KR.
2013
- 프로그램 리뷰 사이트와 Twitter를 통한 TV 프로그램 인기도 비교대한산업공학회/한국경영과학회 춘계공동학술대회, 2013.
- Digital display device and method for controlling the sameUS Patent (Grant US9386342B2). EP Patent (Grant EP2775727B1). CN Patent (Grant CN104038795B). Pending in KR.
2012
- TV 프로그램 정보 기반 자동녹화 방법론 개발한국경영과학회 추계학술대회, 2012.
- Feature selection for identifying high defect density sensors in semiconductor manufacturingINFORMS International. Beijing, China, 2012.
- Parameter adaption for multivariate statistical process control in semiconductor manufacturing using genetic algorithms대한산업공학회/한국경영과학회 춘계공동학술대회, 2012.
- Robust segmentation for sensor data in semiconductor manufacturing한국BI데이터마이닝학회 춘계학술대회, 2012.
2010
- Random Forest 기법을 사용한 저수율 반도체 웨이퍼 검출 및 혐의 설비 탐색한국 BI데이터마이닝학회 추계 학술대회. 2010.
- mRFS: Minimum redundancy feature selection based on a clustering filter한국 BI데이터마이닝학회 추계 학술대회. 2010.
- Feature selection for detecting faulty equipment parameters in semiconductor manufacturing process대한산업공학회 추계학술대회. 2010.