Papers by Hung Luu

2 papers
ViGoEmotions: A Benchmark Dataset For Fine-grained Emotion Detection on Vietnamese Texts (2026.eacl-long)

Copied to clipboard

Challenge: Recent advances in NLP have greatly improved outcomes in emotion prediction and harmful content detection.
Approach: They propose to classify Vietnamese comments into 27 distinct emotions using a model-based lexical normalization system and a transformer-based model.
Outcome: The proposed corpus of 20,664 social media comments is based on a novel model that can support multiple architectures, but its quality and preprocessing strategies remain key factors influencing performance.
HiGraAgent: Dual-Agent Adaptive Reasoning over Hierarchical Knowledge Graph for Open Domain Multi-hop Question Answering (2026.findings-eacl)

Copied to clipboard

Challenge: Existing approaches to multi-hop question answering lack a robust and flexible approach to QA . prior work showed compositionality gap persists even for Large Language Models .
Approach: They propose a framework that unifies graph-based retrieval with adaptive reasoning . HiGraAgent uses a hierarchical knowledge Graph with entity alignment .
Outcome: The proposed framework outperforms the strongest graph-based method on hotpotQA, 2WikiMultihopQA, and MuSiQue.

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