In recent years, visual question answering (VQA) has attracted attention from the research community because of its highly potential applications (such as virtual assistance on intelligent cars, assistant devices for blind people, or information retrieval from document images using natural language as queries) and challenge. The VQA task requires methods that have the ability to fuse the information from questions and images to produce appropriate answers. Neural visual question answering models have achieved tremendous growth on large-scale datasets which are mostly for resource-rich languages such as English. However, available datasets narrow the VQA task as the answers selection task or answer classification task. We argue that this form of VQA is far from human ability and eliminates the challenge of the answering aspect in the VQA task by just selecting answers rather than generating them. In this paper, we introduce the OpenViVQA (Open-domain Vietnamese Visual Question Answering) dataset, the first large-scale dataset for VQA with open-ended answers in Vietnamese, consists of 11,000+ images associated with 37,000+ question-answer pairs (QAs). Moreover, we proposed FST, QuMLAG, and MLPAG which fuse information from images and answers, then use these fused features to construct answers as humans iteratively. Our proposed methods achieve results that are competitive with SOTA models such as SAAA, MCAN, LORA, and M4C. The dataset is available to encourage the research community to develop more generalized algorithms including transformers for low-resource languages such as Vietnamese.
Improving Vietnamese Legal Question--Answering System based on Automatic Data Enrichment
VNU University of Engineering and Technology(越南国立大学工程技术大学);National Institute of Informatics(国立信息学研究所);Japan Advanced Institute of Science and Technology(日本北陆先端科学技术大学院大学)
VLQA: The First Comprehensive, Large, and High-Quality Vietnamese Dataset for Legal Question Answering
Japan Advanced Institute of Science and Technology(日本先进科学研究院);VNU University of Engineering and Technology(VNU工程大学);VNU University of Law(VNU法律大学);National Institute of Informatics(国立信息学研究所)
针对越南语法律 NLP 缺乏高质量标注语料的问题,本文构建并统计分析了全面的 VLQA 数据集,并基于法律信息检索与问答任务用 SOTA 模型评估其有效性。
ViHERMES: A Graph-Grounded Multihop Question Answering Benchmark and System for Vietnamese Healthcare Regulations
URA Research Group, Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), VNU-HCM, Vietnam(URA研究组,计算机科学与工程学院,胡志明市技术大学(HCMUT),VNU-HCM,越南)
ViConsFormer: Constituting Meaningful Phrases of Scene Texts using Transformer-based Method in Vietnamese Text-based Visual Question Answering
Ho Chi Minh city University of Technology(胡志明市理工大学);Vietnam National University, Ho Chi Minh city(越南国家大学胡志明市分校);University of Information Technology(信息技术大学)
A Benchmark Dataset and Evaluation Framework for Vietnamese Large Language Models in Customer Support
URA Research Group, Faculty of Computer Science and Engineering, Ho Chi Minh City University of Technology (HCMUT), Ho Chi Minh City, Vietnam(乌尔拉研究组,计算机科学与工程学院,胡志明城理工大学(HCMUT),胡志明城,越南);Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam(越南国家大学胡志明城分校,胡志明城,越南)
Attentive Deep Neural Networks for Legal Document Retrieval
Japan Advanced Institute of Science and Technology(日本北陆先端科学技术大学院大学);National Institute of Informatics(日本国立信息学研究所);Posts and Telecommunications Institute of Technology(邮电技术学院)
Investigating the Effectiveness of ChatGPT in Mathematical Reasoning and Problem Solving: Evidence from the Vietnamese National High School Graduation Examination
Eastern International University(东方国际大学);International University, VNUHCM(越南国立大学胡志明市国际大学)