Papers by Yung-Yu Chen

3 papers
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations