-
- 031-299-4798
- yjko@skku.edu
-
자연어처리, 대화시스템
관심분야
자연어처리, 정보검색, 대화시스템, 질의응답시스템, 텍스트마이닝
약력/경력
- 2022-현재, 성균관대학교 인공지능학과, 데이터사이언스 융합학과 대학원 학과장
- 2011-2012, 메릴랜드 대학교(College Park, USA), Visiting Scholar
- 1996-1997, LG-EDS Systems Corp., System Engineer
학술지 논문
- (2023) Efficient framework for low-resource abstractive summarization by meta-transfer learning and pointer-generator networks. EXPERT SYSTEMS WITH APPLICATIONS. 234
- (2023) Dicer: Dialogue-Centric Representation for Knowledge-Grounded Dialogue through Contrastive Learning. PATTERN RECOGNITION LETTERS. 172
- (2023) Meta-learning with topic-agnostic representations for zero-shot stance detection. PATTERN RECOGNITION LETTERS. 171
- (2023) Enriching the dialogue state tracking model with a asyntactic discourse graph. PATTERN RECOGNITION LETTERS. 169
- (2023) Graph-based query reformulation system for descriptive queries of jargon words using definitions. EXPERT SYSTEMS WITH APPLICATIONS. 214
- (2023) Knowledge-grounded dialogue modelling with dialogue-state tracking, domain tracking, and entity extraction. COMPUTER SPEECH AND LANGUAGE. 78
- (2023) Knowledge graph extension with a pre-trained language model via unified learning method. KNOWLEDGE-BASED SYSTEMS. 262
- (2022) BERT-based response selection in dialogue systems using utterance attention mechanisms. EXPERT SYSTEMS WITH APPLICATIONS. 209
- (2022) Multitask Fine-Tuning for Passage Re-Ranking Using BM25 and Pseudo Relevance Feedback. IEEE ACCESS. 10
- (2022) Effective fake news video detection using domain knowledge and multimodal data fusion on youtube. PATTERN RECOGNITION LETTERS. 154, -
- (2022) Novel regularization method for the class imbalance problem. EXPERT SYSTEMS WITH APPLICATIONS. 188
- (2021) Effective fake news detection using graph and summarization techniques. PATTERN RECOGNITION LETTERS. 151
- (2021) Using Adversarial Learning and Biterm Topic Model for an Effective Fake News Video Detection System on Heterogeneous Topics and Short Texts. IEEE ACCESS. 9
- (2021) MEM-KGC: Masked Entity Model for Knowledge Graph Completion With Pre-Trained Language Model. IEEE ACCESS. 9
- (2021) Word sense disambiguation based on context selection using knowledge-based word similarity. INFORMATION PROCESSING & MANAGEMENT. 58, 4
- (2021) Parallel sentence extraction to improve cross-language information retrieval from Wikipedia. JOURNAL OF INFORMATION SCIENCE. 47, 2
- (2020) Named-Entity Recognition Using Automatic Construction of Training Data From Social Media Messaging Apps. IEEE ACCESS. 8
- (2020) Construction of Machine-Labeled Data for Improving Named Entity Recognition by Transfer Learning. IEEE ACCESS. 8, 1
- (2020) Simple methods to overcome the limitations of general word representations in natural language processing tasks. COMPUTER SPEECH AND LANGUAGE. 59
- (2019) Improving Neural Machine Translation by Filtering Synthetic Parallel Data. ENTROPY. 21, 12
특허/프로그램
- 가짜 뉴스 동영상 탐지 시스템 및 그의 방법. 10-2021-0022638. 20220817. 대한민국
- 키워드 클러스터링을 이용한 문서 요약 방법 및 장치. 10-2020-0106414. 20220523. 대한민국
- 자모 및 음절 임베딩 결합을 이용하는 한국어 형태소 분석을 위한 장치 및 방법(System and Method for Korean POS Tagging Using the Concatenation of Jamo and Syllable Embedding). 10-2109-8580000. 20200506. 대한민국
- 학습 데이터 확장을 통한 딥러닝 기반 인과관계 추출을 위한 장치 및 방법(System and Method for Extracting Deep Learning Based Causal Relation with Expansion of Training Data). 10-2109-8600000. 20200506. 대한민국
- 합성곱 신경망에 의한 발화 임베딩을 사용한 유사도 측정 기반의 채팅 말뭉치 확장을 위한 장치 및 방법(System and Method for Expansion Chatting Corpus Based on Similarity Measure Using Utterance Embedding by CNN). 10-2109-8660000. 20200506. 대한민국
- 원격지도(Distant Supervision) 기법을 이용한 개체명 인식 프로그램. C-2019-043819. 20191230. 대한민국
- 과학문서의 핵심어구 추출방법 및 장치(keyword extraction method and apparatus for science document). 10-2017-2270000. 20190827. 대한민국
- 언어 분석기별 정답 레이블 분포를 이용한 자연어 이해 방법(Method for Natural Langage Understanding Based on Distribution of Task-specific Labels). 10-2012-4040000. 20190813. 대한민국
수상/공훈
- Winner (1st place), sub-track #1 and #3 of SIMMC 2.0 in DSTC10, 2021.
- 논문 공헌상, 한국정보과학회, 2015.
학술회의논문
- (2023) Never Too Late to Learn: Regularizing Gender Bias in Coreference Resolution. ACM International Conference on Web Search and Data Mining. 싱가포르
- (2022) Lightweight Meta-Learning for Low-Resource Abstractive Summarization. ACM SIGIR Conference on Information Retrieval. 스페인
- (2022) QSG Transformer: Transformer with Query-Attentive Semantic Graph for Query-Focused Summarization. ACM SIGIR Conference on Information Retrieval. 스페인
- (2022) Domain Adaptive Task-Oriented Dialog System for Deep Understanding of Multimodal Conversation. The DSTC10 Workshop in the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022). 미국
- (2022) Adapting Pre-trained Language Model for Dialogue State Tracking on Spoken Conversations. The DSTC10 Workshop in the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022). 미국
- (2022) Various Uses of Pre-trained Language Model for a Knowledge-grounded Task Oriented Dialogue System. The DSTC10 Workshop in the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022). 미국
- (2021) Query Reformulation for Descriptive Queries of JargonWords Using a Knowledge Graph based on a Dictionary. ACM Conference on Information and Knowledge Management. 오스트레일리아
- (2021) Self-Supervised Learning based on Sentiment Analysis withWordWeight Calculation. ACM Conference on Information and Knowledge Management. 오스트레일리아
- (2021) Self-supervised Fine-tuning for Efficient Passage Re-ranking. ACM Conference on Information and Knowledge Management. 오스트레일리아
- (2021) Using Topic Modeling and Adversarial Neural Networks for Fake News Video Detection. ACM Conference on Information and Knowledge Management. 오스트레일리아
- (2021) Fine-grained Post-training for Improving Retrieval-based Dialogue Systems. Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 멕시코
- (2021) Graph-based Fake News Detection using a Summarization Technique. European Association for Computational Linguistics. 우크라이나
- (2021) Improving Multimodal API Prediction via Adding Dialog State and Various Multimodal Gates. DSTC9 Workshop, AAAI-21. 미국
- (2021) TOM : End-to-End Task-Oriented Multimodal Dialog System with GPT-2. DSTC9 Workshop, AAAI-21. 미국
- (2021) Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning. AAAI Conference on Artificial Intelligence. 미국
- (2020) Multi-Task Learning for Knowledge Graph Completion with Pre-trained Language Models. International Conference on Computational Linguistics. 스페인