Jump to: navigation, search

Ongoing Projects

VTT: 주어진 비디오에 대한 인간 수준의 질의응답을 제공하는 비디오 이해 지능 기술
인간 수준의 비디오 이해 지능 및 검증 기술 개발을 목표로 하는 프로젝트로, 비디오 데이터로부터 이벤트 상황에 대한 인지 및 관계추론 기술을 개발하고 한다. This project aims to develop human-level video understanding intelligence and verification technology and develops recognition and relationship inference for event situation from video data.

see more

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).

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.

see more

Emotional intelligence technology to infer human emotion and carry on dialogue accordingly.

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.

Previous Projects

그래프 유사도 기반 문서 내 개체 인식 및 지식베이스 연결
A project to build a Korean syntactic parser. Syntactic parser plays basic role for many natural language processing applications.

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: 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.

Korean Parser
A project to build a Korean syntactic parser. Syntactic parser plays basic role for many natural language processing applications.

The Linked Open Data (LOD) ( is a large-scale integrating project co-funded by the European Commission within the FP7 information and Communication Technologies Work Programe (Grant Agreement No.257943)

Health Avatar
NCRC: Health Avatar
The Health Avatar project aims to mine information of medical knowledge from both literature and Web, and to serve as a support resource for the knowledge engine of Avatar.

The openEBook project signposts future-oriented e-book that can supply users with better knowledge and better interface.

OntoCloud is a project to enrich the ontology using DBpedia as a pivot.

COAT: Manual Semantic Annotation Toolkit
Semantic annotation toolkit is dedicated for fast & easy-to-use semantic annotation. It supports users by easy, keyboard-based graphical interface. Also we are planning to support automatic generation of semantic data.

Intrinsic Property and its applications
Intrinsic property, or rigid property, is a property which represents essentiality of a thing. This research is about mining intrinsic properties of a thing automatically from Wikipedia category structure, and applying it to various fields.

Multilingual Synchronization
Multilingual Synchronization
this research is to synthesize contents of Wikipedia from multiple different language editions.

Semantic Post-It
Semantic Post-It
Semantic Post-it is a configurable memo interface with semantic service plugins. It can analyze the memo contents, augment memo context to give a better view to the user, or zoom on the meaning of specific information word of the memo.

This project object is IT ontology infrastructure and service technology development.

IT ontology infrastructure is consisted of designing and building ontology schema, creating ontology instance and storing ontology
IT ontology service technology object is to commercialize IT ontology infrastructure elements

CoreNet: Core Multilingual Semantic WordNet
CoreNet is a net of words based on their semantics, and could be a useful resource in natural language proessing. Especially, it could act as a important knowledge base for information retrieval and machine translation.

BoRA: Bank of Resource for Language and Annotation
BoRA, Bank of Resoure for Language and Annotation, helps researchers to easily access to those language resources which requires continuous maintenance and distribution.

HanNanum: Korean Morphological Analyzer
Hannanum is a morphological analyzer and a POS tagger which is plug-in component architecture-based tool. Hannanum was developed in Java, so this tool is available in every platform which has JRE.

The construction and standardization of very large scale speech, language, image DB for application
The construction and standardization of very large scale speech, language, image DB for application
The goal of this project is, the construction of standardized databases for Korean speech/language/imagedata.

KIBS: Korean Information Base System
KIBS, Korean Information Base System, is a database developed for Korean information processing technology development. The database collects various Korean resources, tools and information for Korean language researchers and Korean language processing application developers.

KORTERM: Korea Terminology Research Center for Language and Knowledge Engineering
As the major research center of Terminology in Korea, KORTERM aims at systematic research on Terminology.