Kyong-Ho Lee
8 papers · 2019–2026 · 5 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Silver
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(24)
🐣
Hot Topic Early Bird
Top co-authors
Research topics
Natural Language Processing
(7)
Artificial Intelligence
(5)
Machine Learning
(4)
Applications
(4)
Core AI
(4)
Generation
(4)
Deep Learning
(3)
Core Methods
(3)
Learning Types · Machine Learning
(3)
Learning Types · Deep Learning
(2)
Interdisciplinary
(1)
Architectures
(1)
Learning Paradigms
(1)
Linguistics
(1)
Resources & Methods
(1)
Keywords
large language model
(2)
response generation
(2)
knowledge extraction
(1)
relation extraction
(1)
topic modeling
(1)
dialogue generation
(1)
commonsense knowledge
(1)
batch sampling
(1)
emotion recognition
(1)
uncertainty sampling
(1)
knowledge graph
(1)
concept extraction
(1)
pre-trained language model
(1)
multi-turn dialogue
(1)
commonsense reasoning
(1)
attention mechanism
(1)
sentence classification
(1)
triplet loss
(1)
dialogue system
(1)
contrastive learning
(1)
Papers
LLMs as Knowledge Graph Refiners: Mitigating Factual Inconsistencies in Generative Knowledge Extraction
ACL 2026
VSPO: Validating Semantic Pitfalls in Ontology via LLM-Based CQ Generation
AAAI 2026
CLICK: Contrastive Learning for Injecting Contextual Knowledge to Conversational Recommender System
EACL 2023
Concept-based Persona Expansion for Improving Diversity of Persona-Grounded Dialogue
EACL 2023
Persona Expansion with Commonsense Knowledge for Diverse and Consistent Response Generation
EACL 2023
Active Learning on Pre-trained Language Model with Task-Independent Triplet Loss
AAAI 2022
Emp-RFT: Empathetic Response Generation via Recognizing Feature Transitions between Utterances
NAACL 2022
Topic-Guided Coherence Modeling for Sentence Ordering by Preserving Global and Local Information
EMNLP 2019