Joongmin Shin

Publications / Journals

Distance Based Korean WordNet (alias. KorLex) Embedding Model

Applied Artificial Intelligence 38(1), Taylor & Francis · Sep 2024

SeongReol Park*, Joongmin Shin, Sanghyun Cho, Hyuk-Chul Kwon, Jung-Hun Lee

Paper

KorLex embedding model architecture
KorLex embedding model architecture — click to open the full-resolution figure.

Abstract

This paper maps KorLex lexical knowledge into vector space to inject graph-aware semantics into representation learning. The approach improves lexical similarity behavior compared with purely distributional baselines.

Key Contribution

Graph-aware lexical embedding model that injects structured knowledge into vector representations.

knowledge graphembeddingKorean NLP