Home

From SWRC

Jump to: navigation, search


The Semantic Web Research Center (SWRC) is a research center committed to the study of the next-generation semantic web, and to the development of the basic infrastructural technologies to lead the coming semantic web era, based on technologies such as ontology construction and neuro-scientific artificial intelligence creation that will be the foundation of the future world. Founded in 1998 as the Korea Terminology Research Center For Language And Knowledge Engineering (KORTERM), SWRC was established as the research in terminology and language engineering was expanding into studies advancing the ontology of the next-generation semantic web, including technologies such as inference engines, knowledge portals, and ubiquitous brokers. The center’s immediate objective is to increase the capacity within KAIST to make KAIST the forerunner in the field of semantic web, and to enhance the participation of professors and researchers, in order to develop the center into a representative national and international research organization. more ...



Activities

OKBQA_2016
OKBQA-2016 (Open Knowledge Base and Question Answering Workshop at COLING)
The Workshop on Open Knowledge Base and Question Answering Workshop (OKBQA 2016) took place in Osaka on 11 December 2016, as part of COLING 2016.

The main goal of this workshop is to join forces in the collaborative development of open frameworks for knowledge extraction and question answering, to share standards, and to foster the creation of an ecosystem of tools and benchmarks. The call for papers for OKBQA 2016 was issued in September 2016 and elicited a good number of high- quality submissions, each of which was peer-reviewed by three members of the programme committee. At the end we accepted six submissions as long papers, and ten as short papers. Our technical programme combined five oral long papers, two oral short papers and seven poster papers. Please refer to the homepage for more detailed information.

http://coling2016.okbqa.org


OKBQA_4
OKBQA-4 (The 4th International Hackathon on Open Knowledge Base and Question-Answering)
우리 연구실 주최 국제행사인 OKBQA-4 (The 4th International Hackathon on Open Knowledge Base and Question-Answering)이 지난 7월 16일부터 21일까지 제주대학교 국제교류회관에서 개최되었습니다.

자연언어질의와 지식베이스구축을 주제로 하는 오픈프로젝트인 OKBQA는 개발자간 협력체계를 구축하고 새로운 개발자의 진입장벽을 낮추기 위해 전체 QA 시스템을 하나의 파이프라인으로 구성할 수 있는 플랫폼을 제작하는것을 목표로 합니다. 한국의 카이스트, 독일의 라이프찌히대학/빌레펠트대학, 일본의 생명과학데이터베이스센터 및 다양한 국제 그룹의 개발자 및 연구원들의 참여를 통해 개최된 4회째 OBKQA 튜토리얼, 심포지엄, 해커톤의 자세한 사항은 해당 홈페이지에서 확인하실 수 있습니다. http://2016.okbqa.org/

+ 대회기간 내 BEST PERFORMANCE AWARD는 강명구(Peter Khang)로 선정되었습니다. 축하드립니다. 더불어, 2016년 12월에 개최되는 COLING 2016에 OKBQA 관련 워크샵이 개최될 예정이며 많은 분들의 관심 부탁드립니다.

http://coling2016.okbqa.org


… further results


2016 Invited Talk by Jaeyoung Choi (ICSI UC Berkeley)
2016 Invited Talk by Jaeyoung Choi (ICSI UC Berkeley)
On Monday the 4th of January 2016, Jaeyoung Choi – a staff researcher from the International Computer Science Institute (ICSI) of the University of California (UC), Berkeley, USA – visited KAIST’s School of Computing at the invitation of Semantic Web Research Center (SWRC) and gave a talk on the subject of "From Crowdsourcing to Deep Learning: Multimodal Methods and Model for Web-scale Multimedia Collection".

Professor Key-Sun Choi received the Order of Service Merit for his contribution to the development and promotion of Hangeul
Professor Key-Sun Choi received the Order of Service Merit for his contribution to the development and promotion of Hangeul
At the opening ceremony of commemorating the 569th anniversary of the proclamation of Hangeul that was held at the Sejong Center last Friday, the 9th of October, Professor Key-Sun Choi of KAIST’s School of Computing was conferred the Order of Service Merit Aquamarine Stripes Medal (Hangeul: 옥조근정훈장, Hanja: 玉條勤政勳章) for his distinguished, life-long contribution to the development and promotion of Hangeul and the Korean language. Professor Choi has not only developed a natural language processing parser that enables effective data-processing of Hangeul and the Korean language, but also internationally commercialized its sharing software. Professor Choi has been contributing greatly to the informatization of Hangeul in many different ways as well, by constructing Korean-language-oriented dictionaries for computers and so forth. Having acknowledged his such ability and effort both at national and international level, Professor Choi is continuing to play a leading role in a wide variety of academic conferences and standardization organizations.

Hosted NLIWOD 2014
Hosted NLIWOD 2014
Hosted NLIWOD 2014

Ph.D Student. Younggyun Hahm Received The Best Paper Award
Ph.D Student. Younggyun Hahm Received The Best Paper Award
Ph.D Student. Younggyun Hahm received the "Best Paper Award" at the 26th Annual Conference on Human & Cognitive Language Technology(HCLT)

… further results


Recent Research

PACS
폐, 간, 심질환 영상판독지원을 위한 인공지능 원천기술개발 및 PACS 연계 상용화
인공지능 기반 자연어처리 기술을 활용하여 다형(multi-modal)의 EMR데이터로부터 구조화된 지식을 학습하고, 이를 의료영상의 학습을 통한 의료지식과 융합하여, 통합된 의료지식을 획득.

획득된 지식을 통해 진단 의사, 진단 환경, 환자, 질환별 다면 분석을 실행하고 차후 발생할 판독 오류를 감소시켜 효과적인 환자 진단. 의료진 개개인의 검사 및 판독 패턴을 학습하여 의사별로 개별화된 정밀의료 검색 및 판독 시스템을 구현하여, 의료진의 시간을 최소화. 환자와 보호자의 장황한 설명을 요약하고, 의사의 처방 및 진단서 작성을 보조하는, 자연어(문법, 문맥)와 의료지식에 기반한 문서작성 도우미(에이전트). 자연어처리 기술을 이용한 챗봇(ChatBot) 결합 응용 서비스 제공(예: 의료 관련 문서 검색 서비스, 규칙 기반 질의/응답 엔진).


Emotion
상대방의 감성을 추론, 판단하여 그에 맞추어 대화하고 대응할 수 있는 감성지능 기술 연구개발
인간과 유사하게 대화하면서 상대방의 감정을 추론, 판단하여 감성적 대화를 통해 정서적인 공감대를 형성할 수 있는 자율지능 디지털 동반자용 감성지능 개발. Emotional intelligence technology to infer human emotion and carry on dialogue accordingly.

BII
BII: Bio Image Informatics
의료 관련 데이터 (EMR 데이터, 유전체 영상 분석 결과, 세포 영상 분석 결과) 등의 다면 데이터로부터 숨겨진 혹은 관심을 가질 만한 연관관계를 발견해내기 위하여, 전자 의무 기록 (EMR) 내에서 용어를 탐지하고 추출하는 자동화된 과정을 설계하는 것이 SWRC의 Bio & Medical Informatics 프로젝트의 연구 내용이다.

SWRC's Bio & Medical Informatics Project is about automatic extraction and detection of terms from electronic medical records (EMR) to discover hidden / interesting correlations of multi-faceted data.


QAMEL
QAMEL: Question Answering on Mobil Devices
In this research project, we will develop a resource-aware and generic multimodal question answering (QA) framework for mobile devices. AMEL will support speech, text and gestures as input. Moreover, QAMEL will use the distribution of the data to improve the execution of queries in both offline and online modes. We will deliver an open-source framework that implements (1) multimodal QA, (2) feedback processing functionality as well as (3) prototypical extensions of the partners’ product suites and use case studies.

Exobrain
Exobrain
Construction, Expansion and Validation of knowledge bases through self-learning and reasoning technologies of machines.

DBpedia Korea
DBpedia Korea
The DBpedia Korea project aims to extract structured datasets from Wikipedia in Korean.