paper-with-me

홈 › Papers

SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking

2025-03-02 · Dien X. Tran, Nam V. Nguyen, Thanh T. Tran, Anh T. Hoang, Tai V. Duong, Di T. Le, Phuc-Lu Le

The rise of misinformation, exacerbated by Large Language Models (LLMs) like GPT and Gemini, demands robust fact-checking solutions, especially for low-resource languages like Vietnamese. Existing methods struggle with semantic ambiguity, homonyms, and complex linguistic structures, often trading accuracy for efficiency. We introduce SemViQA, a novel Vietnamese fact-checking framework integrating Semantic-based Evidence Retrieval (SER) and Two-step Verdict Classification (TVC). Our approach balances precision and speed, achieving state-of-the-art results with 78.97\% strict accuracy on ISE-DSC01 and 80.82\% on ViWikiFC, securing 1st place in the UIT Data Science Challenge. Additionally, SemViQA Faster improves inference speed 7x while maintaining competitive accuracy. SemViQA sets a new benchmark for Vietnamese fact verification, advancing the fight against misinformation. The source code is available at: https://github.com/DAVID-NGUYEN-S16/SemViQA.

📄 PDF Abstract BibTeX arXiv:2503.00955

Code (1)

DAVID-NGUYEN-S16/SemViQA 공식 구현 pytorch

Tasks

Fact CheckingFact VerificationInformation RetrievalMisinformationQuestion AnsweringVietnamese Fact Checking

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

A Vietnamese Question Answering System

2019-11-26 · Dai Quoc Nguyen, Dat Quoc Nguyen, Son Bao Pham

Question answering systems aim to produce exact answers to users' questions instead of a list of related documents as used by current search engines. In this paper, we propose an ontology-based Vietnamese question answer…

Question Answering

A Factoid Question Answering System for Vietnamese

2018-03-02 · Phuong Le-Hong, Duc-Thien Bui

In this paper, we describe the development of an end-to-end factoid question answering system for the Vietnamese language. This system combines both statistical models and ontology-based methods in a chain of processing …

General KnowledgeQuestion Answering

Ripple Down Rules for Question Answering

2014-12-12 · Dat Quoc Nguyen, Dai Quoc Nguyen, Son Bao Pham

Recent years have witnessed a new trend of building ontology-based question answering systems. These systems use semantic web information to produce more precise answers to users' queries. However, these systems are most…

Question Answering

Generative Pre-trained Transformer for Vietnamese Community-based COVID-19 Question Answering

2023-10-23 · Tam Minh Vo, Khiem Vinh Tran

Recent studies have provided empirical evidence of the wide-ranging potential of Generative Pre-trained Transformer (GPT), a pretrained language model, in the field of natural language processing. GPT has been effectivel…

DecoderLanguage ModelingLanguage ModellingQuestion Answering

A Vietnamese Text-Based Conversational Agent

2019-11-26 · Dai Quoc Nguyen, Dat Quoc Nguyen, Son Bao Pham

This paper introduces a Vietnamese text-based conversational agent architecture on specific knowledge domain which is integrated in a question answering system. When the question answering system fails to provide answers…

Question Answering