Papers by Son Nguyen

6 papers
VlogQA: Task, Dataset, and Baseline Models for Vietnamese Spoken-Based Machine Reading Comprehension (2024.eacl-long)

Copied to clipboard

Challenge: Existing datasets for machine reading comprehension tasks in Vietnamese focus on written documents, such as Wikipedia articles, online newspapers, or textbooks.
Approach: They propose to capture Vietnamese spoken language in natural settings and use it to create a machine-learning corpus for machine reading comprehension tasks.
Outcome: The proposed corpus consists of 10,076 question-answer pairs based on 1,230 transcript documents sourced from YouTube .
Enhance Incomplete Utterance Restoration by Joint Learning Token Extraction and Text Generation (2022.naacl-main)

Copied to clipboard

Challenge: omitted tokens from the context contribute to incomplete utterance restoration (IUR) understanding conversational interactions through NLP has become important with increasing connectivity and range of capabilities.
Approach: They propose a model for incomplete utterance restoration called JET . they construct a Picker that identifies omitted tokens and two label creation methods to support the picker.
Outcome: The proposed model is better than pretrained T5 and non-generative language model methods on four benchmark datasets in extraction and abstraction scenarios.
VLUE: A New Benchmark and Multi-task Knowledge Transfer Learning for Vietnamese Natural Language Understanding (2024.findings-naacl)

Copied to clipboard

Challenge: a lack of standard evaluation metrics and benchmarks makes it difficult to identify strengths of Vietnamese NLP models.
Approach: They propose to establish a standardized set of benchmarks for Vietnamese NLU . they propose to evaluate Vietnamese language understanding models using a pre-trained model .
Outcome: The proposed model combines proficiency of a multilingual pre-trained model with Vietnamese linguistic knowledge.
Region-Grounded Report Generation for 3D Medical Imaging: A Fine-Grained Dataset and Graph-Enhanced Framework (2026.acl-long)

Copied to clipboard

Challenge: Current methods map whole volumes to reports, ignoring the clinical workflow of analyzing localized Regions of Interest (RoIs) Current models exhibit suboptimal accuracy and are prone to significant hallucinations.
Approach: They propose a framework that mimics the professional radiologist diagnostic workflow by employing graph-based relational modules to capture dependencies between RoI attributes.
Outcome: The proposed framework surpasses existing models by 19.7% in BLEU and 4.7% in ROUGE-L while achieving a 45.8% improvement in clinical metrics.
VMLU Benchmarks: A comprehensive benchmark toolkit for Vietnamese LLMs (2025.acl-long)

Copied to clipboard

Challenge: The evolution of Large Language Models (LLMs) has underscored the need for benchmarks designed for various languages and cultural contexts.
Approach: They propose to use Vietnamese multitask language understanding (VMLU) benchmarks to assess different capabilities of LLMs, including general knowledge, reading comprehension, reasoning, and conversational skills.
Outcome: The VMLU Benchmarks assess LLMs' general knowledge, reading comprehension, reasoning, and conversational skills.
Conversation Understanding using Relational Temporal Graph Neural Networks with Auxiliary Cross-Modality Interaction (2023.emnlp-main)

Copied to clipboard

Challenge: Emotion recognition is a crucial task for human conversation understanding . multimodal data, e.g., language, voice, and facial expressions, add complexity to the task.
Approach: They propose a relational temporal Graph Neural Network with Auxiliary Cross-Modality Interaction framework that captures conversation-level cross-modality interactions and utterance-level temporal dependencies with modality-specific manner for conversation understanding.
Outcome: The proposed framework captures conversation-level cross-modality interactions and utterance-level temporal dependencies with the modality-specific manner for conversation understanding.

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