Bonggeun Choi

ORCID: 0000-0001-5689-9789
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Topic Modeling
  • Natural Language Processing Techniques
  • Advanced Graph Neural Networks
  • Data Quality and Management
  • Speech and dialogue systems

Sungkyunkwan University
2021-2023

The knowledge graph completion (KGC) task aims to predict missing links in graphs. Recently, several KGC models based on translational distance or semantic matching methods have been proposed and achieved meaningful results. However, existing a significant shortcoming–they cannot train entity embedding when an does not appear the training phase. As result, such use randomly initialized embeddings for entities that are unseen phase cause critical decrease performance during test To solve this...

10.1109/access.2021.3113329 article EN cc-by IEEE Access 2021-01-01
Coming Soon ...