A Community-Based Vietnamese Question Answering System

Tran, Quan Hung; Nguyen, Nien Dinh; Duc, Kien; Nguyen, Thinh Khanh; Dat, Tran Do; Nguyen, Minh Le; Pham, Son Bao

doi:10.1007/978-3-319-11680-8_10

Cited by 4 publications

(12 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While there are myriad benchmarks for the Visual Question Answering (VQA) task in English [33], languages with scarce linguistic resources, such as Vietnamese, face a notable dearth of such resources. In a significant stride in 2021, Tran et al [7] launched the ViVQA dataset, marking the inception of a dedicated VQA dataset for Vietnamese. To craft this dataset, machine translation techniques were harnessed to transcribe questions and answers from a segment of the VQAv2 dataset into Vietnamese, followed by an exhaustive verification to ensure the accuracy and fluency of the translations.…”

Section: Related Workmentioning

confidence: 99%

“…Taking into consideration the conceivable complications associated with validation and the intrinsic constraints of outcomes derived from machine translation, the efficacy of the semi-automated approach introduced in [7] may not ascertain performance at a human level in the translation of an English VQA dataset into Vietnamese. As a result, the credibility of the ViVQA dataset as a benchmark may be compromised for executing experimental procedures, assessing VQA systems, or fostering advancements in Vietnamese VQA research.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese

Tran,

Phan,

Nguyen

et al. 2023

Preprint

View full text Add to dashboard Cite

In recent years, Visual Question Answering (VQA) has gained significant attention for its diverse applications, including intelligent car assistance, aiding visually impaired individuals, and document image information retrieval using natural language queries. VQA requires effective integration of information from questions and images to generate accurate answers. Neural models for VQA have made remarkable progress on large-scale datasets, with a primary focus on resource-rich languages like English.To address this, we introduce the ViCLEVR dataset, a pioneering collection for evaluating various visual reasoning capabilities in Vietnamese while mitigating biases. The dataset comprises over 26,000 images and 30,000 question-answer pairs (QAs), each question annotated to specify the type of reasoning involved. Leveraging this dataset, we conduct a comprehensive analysis of contemporary visual reasoning systems, offering valuable insights into their strengths and limitations.Furthermore, we present PhoVIT, a comprehensive multimodal fusion that identifies objects in images based on questions. The architecture effectively employs transformers to enable simultaneous reasoning over textual and visual data, merging both modalities at an early model stage. The experimental findings demonstrate that our proposed model achieves state-of-the-art performance across seven evaluation metrics.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese

Tran,

Phan,

Nguyen

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The architecture of our question answering system [17] is shown in Figure 1. It includes three modules: Database Construction, Question Analysis and Answer selection, in which the database construction module aims to build the database of question-answer pairs, while the question analysis module extract the useful information such keywords, question types and synonyms.…”

Section: The Vncqas System Architecturementioning

confidence: 99%

Question Analysis for a Community-Based Vietnamese Question Answering System

Tran

Nguyen

Pham

2015

Advances in Intelligent Systems and Computing

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes the approach for analyzing questions in our community-based Vietnamese question answering system (VnCQAs), in which we focus on two subtasks: question classification and keyword identification. The question classification employs the machine learning approaches with a feature which represents a measure of similarity between two questions, while the keyword identification uses the dependency-tree-based features. Experimental results are promising, in which the question classification obtains the accuracy of 95.7% and the keyword identification gains the accuracy of 85.8%. Furthermore, these two subtasks help to improve the accuracy for finding the similar questions in our VnCQAs by 6.75%.

show abstract

“…Their model leverages CNNs and attention mechanisms to extract and align important information between a question and a legal article. Other works on Vietnamese question answering include Nguyen et al [22], Tran et al [29], and Le-Hong and Bui [15].…”

Section: Related Workmentioning

confidence: 99%

“…Question answering (QA) [7,12,22,28,29,30], a sub-field of natural language processing (NLP) and information retrieval (IR), aims to build computer systems that can automatically answer questions in natural languages. There are two main approaches for building QA systems: IR-based and knowledge-based.…”

Section: Introductionmentioning

confidence: 99%

Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers

Uyen²,

Phương³

et al. 2021

Neural Information Processing

View full text Add to dashboard Cite

In this paper, we propose using deep neural networks to extract important information from Vietnamese legal questions, a fundamental task towards building a question answering system in the legal domain. Given a legal question in natural language, the goal is to extract all the segments that contain the needed information to answer the question. We introduce a deep model that solves the task in three stages. First, our model leverages recent advanced autoencoding language models to produce contextual word embeddings, which are then combined with character-level and POS-tag information to form word representations. Next, bidirectional long short-term memory networks are employed to capture the relations among words and generate sentence-level representations. At the third stage, borrowing ideas from graph-based dependency parsing methods which provide a global view on the input sentence, we use biaffine classifiers to estimate the probability of each pair of start-end words to be an important segment. Experimental results on a public Vietnamese legal dataset show that our model outperforms the previous work by a large margin, achieving 94.79% in the F1 score. The results also prove the effectiveness of using contextual features extracted from pre-trained language models combined with other types of features such as character-level and POS-tag features when training on a limited dataset.

show abstract

A Community-Based Vietnamese Question Answering System

Cited by 4 publications

References 12 publications

ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese

ViCLEVR: A Visual Reasoning Dataset and Hybrid Multimodal Fusion Model for Visual Question Answering in Vietnamese

Question Analysis for a Community-Based Vietnamese Question Answering System

Analyzing Vietnamese Legal Questions Using Deep Neural Networks with Biaffine Classifiers

Contact Info

Product

Resources

About