Papers by Yung-Yu Chen
VisTW: Benchmarking Vision-Language Models for Taiwanese Mandarin in Taiwan (2026.findings-acl)
Copied to clipboard
| Challenge: | Vision-Language Models (VLMs) struggle in Taiwanese Mandarin environments due to region-specific orthographic and cultural context. |
| Approach: | They propose a human-grounded purity penalty for character mixing under Taiwanese-Mandarin-style prompts. |
| Outcome: | The proposed model outperforms the strongest open-weight baseline by 22 percentage points on dialogue tasks. |
Knowledge Graph Embeddings in Geometric Algebras (2020.coling-main)
Copied to clipboard
| Challenge: | Existing knowledge graph embedding approaches model entities and relations in KGs using real-valued, complex-value, or hypercomplex-value representations. |
| Approach: | They propose a geometric algebra-based KG embedding framework which uses multivector representations and the geometric product to model entities and relations. |
| Outcome: | The proposed framework outperforms state-of-the-art models for link prediction. |
Temporal Knowledge Graph Completion using a Linear Temporal Regularizer and Multivector Embeddings (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing knowledge graphs involve evolving data, e.g., the fact (The President of the United States is Barack Obama) is valid only from 2009 to 2017. |
| Approach: | They propose a time-aware knowledge graph embebdding approach which performs 4th-order tensor factorization of a Temporal knowledge graph using a Linear temporal regularizer and Multivector embeddings. |
| Outcome: | The proposed model achieves state-of-the-art performance over four well-established temporal knowledge graph completion benchmarks. |