Le Minh Nguyen

• Japan Advanced Institute of Science and Technology

Web applications are critical to modern software ecosystems, yet ensuring their reliability remains challenging due to the complexity and dynamic nature of web interfaces. Recent advances in large language models (LLMs) have shown promise in automating complex tasks, but limitations persist in handling dynamic navigation flows and complex form inte...

With the rapid advancement of global digitalization, users from different countries increasingly rely on social media for information exchange. In this context, multilingual multi-label emotion detection has emerged as a critical research area. This study addresses SemEval-2025 Task 11: Bridging the Gap in Text-Based Emotion Detection. Our paper fo...

Automated fact-checking is crucial for minimizing the effect of misleading information in the vast development of social networks era. However, fact-checking is a challenging task since the claim can have multiple evidence and the information in the evidence is diverse and complex, which needs an efficient method to combine and process to exploit v...

Pre-trained language models have become popular in natural language processing tasks, but their inner workings and knowledge acquisition processes remain unclear. To address this issue, we introduce K-Bloom—a refined search-and-score mechanism tailored for seed-guided exploration in pre-trained language models, ensuring both accuracy and efficiency...

Introduction Accurate image segmentation is crucial in medical imaging for quantifying diseases, assessing prognosis, and evaluating treatment outcomes. However, existing methods often fall short in integrating global and local features in a meaningful way, failing to give sufficient attention to abnormal regions and boundary details in medical ima...

In this paper, we propose ZeFaV - a zero-shot based fact-checking verification framework to enhance the performance on fact verification task of large language models by leveraging the in-context learning ability of large language models to extract the relations among the entities within a claim, re-organized the information from the evidence in a...

Video-based sign language recognition is vital for improving communication for the deaf and hard of hearing. Creating and maintaining quality of Thai sign language video datasets is challenging due to a lack of resources. Tackling this issue, we rigorously investigate a design and development of deep learning-based system for Thai Finger Spelling r...

Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional U-Net architectures and their transformer-integrated variants excel in automated segmentation tasks. Existing models also struggle with parameter efficiency and computational complexity, often due to the extensive use of Transforme...

The Competition on Legal Information Extraction and Entailment (COLIEE) is a well-known international competition organized each year with the goal of applying machine learning algorithms and techniques in the analysis and understanding of legal documents. Two main applications of using machine learning in this domain are entailment and information...

Advances in deep learning have revolutionized medical image segmentation, facilitating the precise delineation of complex anatomical structures. The scarcity of annotated training samples remains a significant bottleneck. To tackle the data limitation, federated learning (FL) offers the promise of pooling data from multiple healthcare institutions....

The rapid growth of the tourism industry has spurred extensive research into tourist route planning. However, existing studies primarily focus on route planning for individual tourists, leaving a notable gap in addressing multiple tourists planning scenarios. Traditional methods for multiple tourists planning, derived from single tourist frameworks...

Named Entity Recognition and Relation Extraction are two crucial and challenging subtasks in the field of Information Extraction . Despite the successes achieved by the traditional approaches, fundamental research questions remain open. First, most recent studies use parameter sharing for a single subtask or shared features for both two subtasks,...

Question-Answering (QA) systems have increasingly drawn much interest in the research community. A significant number of methods and datasets are proposed for the QA tasks. One of the gold standard QA resources is span-extraction Machine Reading Comprehension datasets, where the system must extract a span of text from the context to answer the ques...

Scene text image super-resolution (STISR) is regarded as the process of improving the image quality of low-resolution scene text images to improve text recognition accuracy. Recently, a text attention network was introduced to reconstruct high-resolution scene text images; the backbone method involved the convolutional neural network-based and tran...

In this study, we proposed an efficient method to improve the performance of the hierarchical semantic parsing task by strengthening the meaning representation of the label candidate set via inductive grammar. In particular, grammar was first synthesized from the logical representations of training annotated data. Then, the model utilizes it as add...

Question answering (QA) in law is a challenging problem because legal documents are much more complicated than normal texts in terms of terminology, structure, and temporal and logical relationships. It is even more difficult to perform legal QA for low-resource languages like Vietnamese where labeled data are rare and pre-trained language models a...

Competition on Legal Information Extraction/Entailment (COLIEE) is an annual competition associated with the International Workshop in Juris-Informatics. The challenge for this competition is required not only the skills in processing long documents but also the ability to resolve ambiguity in the legal domain. For lengthy documents, we proposed a...

Medical visual question answering task requires a framework to understand a medical question in natural language and examine the corresponding image to produce the answer to the question. The common framework consists of a language understanding module, a visual understanding module, a signal fusion module, and an answer prediction module. Most exi...

This paper studies Web document summarization by exploiting social information. The motivation comes from the fact that social context of a Web document provides additional information to enrich the content of sentences. To take advantage of such information, we design a model based on Convolutional Neural Networks. Unlike traditional ones, our mod...

With the further development of knowledge graphs, many weighted knowledge graphs (WKGs) have been published and greatly promote various applications. However, current deterministic knowledge graph embedding algorithms cannot encode weighted knowledge graphs well. This paper gives a promising framework WeExt that can extend deterministic knowledge...

Legal text retrieval serves as a key component in a wide range of legal text processing tasks such as legal question answering, legal case entailment, and statute law retrieval. The performance of legal text retrieval depends, to a large extent, on the representation of text, both query and legal documents. Based on good representations, a legal te...

Legal text retrieval serves as a key component in a wide range of legal text processing tasks such as legal question answering, legal case entailment, and statute law retrieval. The performance of legal text retrieval depends, to a large extent, on the representation of text, both query and legal documents. Based on good representations, a legal te...

General Data Protection Regulation (GDPR) is an important framework for data protection that applies to all European Union countries. Recently, DAPRECO knowledge base (KB) which is a repository of if-then rules written in LegalRuleML as a formal logic representation of GDPR has been introduced to assist compliance checking. DAPRECO KB is, however,...

This paper proposes PatternAttack to mitigate two major issues of Adversarial Transformation Network (ATN) including the low diversity and the low quality of adversarial examples. In order to deal with the first issue, this research proposes a stacked convolutional autoencoder based on patterns to generalize ATN. This proposed autoencoder could sup...

Semantic parsing is a challenging task mapping a natural language utterance to machine-understandable information representation. Recently, approaches using neural machine translation (NMT) have achieved many promising results, especially the Transformer. However, the typical drawback of adapting the vanilla Transformer to semantic parsing is that...

The information retrieval task for statute law requires a system to retrieve the relevant legal articles given a legal bar exam query. The Transformer-based approaches have demonstrated robustness over traditional machine learning and information retrieval methods for legal documents. However, those approaches are mainly domain adaptation without a...

As readers of scientific articles often read to answer specific questions, the task of Question-Answering (QA) in academic papers was proposed to evaluate the ability of intelligent systems to answer questions in long scientific documents. Due to the large contexts in the questions, this task poses many challenges to state-of-the-art QA models. Thi...

We introduce efficient deep learning-based methods for legal document processing including Legal Document Retrieval and Legal Question Answering tasks in the Automated Legal Question Answering Competition (ALQAC 2022). In this competition, we achieve 1\textsuperscript{st} place in the first task and 3\textsuperscript{rd} place in the second task. O...

In most applications, text understanding and representation always play an important role, especially in automatic processing. Together with the surface features of words, topic information is highly meaningful and essential to provide the context meaning in the text representation. Recently, the integration of linguistic features and topic informa...

Answerability Prediction on Visual Question Answering is an attractive and novel multi-modal task that can be regarded as a fundamental filter to eliminate the low-qualified samples in practical systems. Instead of focusing on the similarity between images and texts, the critical concern in this task is to accentuate the conflict in visual and text...

Pretrained embeddings have proven effective in legal problems in English. Even so, working well in one language does not guarantee that these models have an advantage in other languages. Understanding the characteristics of these models in a particular language helps us to make more accurate decisions when choosing technology for problems in that l...

Case law retrieval is the task of locating truly relevant legal cases given an input query case. Unlike information retrieval for general texts, this task is more complex with two phases (legal case retrieval and legal case entailment) and much harder due to a number of reasons. First, both the query and candidate cases are long documents consistin...

Data sparsity is one of the challenges for low-resource language pairs in Neural Machine Translation (NMT). Previous works have presented different approaches for data augmentation, but they mostly require additional resources and obtain low-quality dummy data in the low-resource issue. This paper proposes a simple and effective novel for generatin...

A noise-enhanced super-resolution generative adversarial network plus (nESRGAN+) was proposed to improve the enhanced super-resolution GAN (ESRGAN). The contributions of nESRGAN+ generate an impressive reconstructed image with more texture details and greater sharpness. However, the perceptual quality of the output lacks hallucinated details and un...

Touring route planning is an essential part of e-tourism, and significantly aids the development of the tourism industry. Several models have been proposed to formalize the touring route-planning problem with promising results. Most existing models consider only one tourist and return the same or similar results to tourists if they issue the same o...

DeepCheck is a symbolic execution-based method to attack feed-forward neural networks. However, in the untargeted attack, DeepCheck suffers from a low success rate due to the limitation of preserving neuron activation patterns and the weakness of solving the constraint by SMT solvers. Therefore, this paper proposes a method to improve the success r...

Natural language processing techniques contribute more and more in analyzing legal documents recently, which supports the implementation of laws and rules using computers. Previous approaches in representing a legal sentence often based on logical patterns that illustrate the relations between concepts in the sentence, often consist of multiple wor...

Despite the long-standing appearance of question types in the Visual Question Answering dataset, Visual Question Classification does not receive enough public interest in research. Different from general text classification, a visual question requires an understanding of visual and textual features simultaneously. Together with the enthusiasm and n...

In this paper, we introduce our approaches using Transformer-based models for different problems of the COLIEE 2021 automatic legal text processing competition. Automated processing of legal documents is a challenging task because of the characteristics of legal documents as well as the limitation of the amount of data. With our detailed experiment...

In this paper, we introduce our approaches using Transformer-based models for different problems of the COLIEE 2021 automatic legal text processing competition. Automated processing of legal documents is a challenging task because of the characteristics of legal documents as well as the limitation of the amount of data. With our detailed experiment...

Automatic post-editing (APE) research aims to investigate methods for correcting systematic errors in machine translation (MT) results. Recent work has shown successful practices of APE for improving MT output quality; however, their effectiveness strongly relies on the availability of large-scale human-created APE triplets. The high production cos...

The visual impairment community especially blind people needs support from advanced technologies to help them with understanding and answering the image content. In the multi-modal area, Visual Question Answering (VQA) is the notable cutting-edge task requiring the combination of images and texts via a co-attention mechanism. Inspired by the Deep C...

COLIEE is an annual competition in automatic computerized legal text processing. Automatic legal document processing is an ambitious goal, and the structure and semantics of the law are often far more complex than everyday language. In this article, we survey and report our methods and experimental results in using deep learning in legal document p...

Ambiguity is a characteristic of natural language, which makes expression ideas flexible. However, in a domain that requires accurate statements, it becomes a barrier. Specifically, a single word can have many meanings and multiple words can have the same meaning. When translating a text into a foreign language, the translator needs to determine th...

Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs' joint training. This paper proposes two simple strategies to address the rare word issue in multilingual MT systems for two low-resource language pairs: French-Vietnamese and English-Viet...

We present our method for tackling a legal case retrieval task by introducing our method of encoding documents by summarizing them into continuous vector space via our phrase scoring framework utilizing deep neural networks. On the other hand, we explore the benefits from combining lexical features and latent features generated with neural networks...

We propose deep learning based methods for automatic systems of legal retrieval and legal question-answering in COLIEE 2020. These systems are all characterized by being pre-trained on large amounts of data before being finetuned for the specified tasks. This approach helps to overcome the data scarcity and achieve good performance, thus can be use...

We present our method for tackling the legal case retrieval task of the Competition on Legal Information Extraction/Entailment 2019. Our approach is based on the idea that summarization is important for retrieval. On one hand, we adopt a summarization based model called encoded summarization which encodes a given document into continuous vector spa...

We propose a joint model for POS tagging and dependency parsing. Our model consists of a BiLSTM-CNN-CRF-based POS tagger [26] and a Deep Biaffine Attention-based dependency parser [24]. A combined objective function is used to jointly train both models. Experiment results show very competitive performance on several languages of the Universal Depen...

This book constitutes the refereed proceedings of the 16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, held in Hanoi, Vietnam, in October 2019. The 28 full papers and 14 short papers presented were carefully reviewed and selected from 70 submissions. The papers are organized in topical sections o...

Among the six challenges of neural machine translation (NMT) coined by (Koehn and Knowles, 2017), rare-word problem is considered the most severe one, especially in translation of low-resource languages. In this paper, we propose three solutions to address the rare words in neural machine translation systems. First, we enhance source context to pre...

While translating between Chinese-centric languages, many works have discovered clear advantages of using characters as the translation unit. Unfortunately, traditional recurrent neural machine translation systems hinder the practical usage of those character-based systems due to their architectural limitations. They are unfavorable in handling ext...

Recently research in opinions summarization focuses on rating expressions by aspects and/or sentiments they carry. To extract aspects of an expression, most studies require a predefined list of aspects or at least the number of aspects. Instead of extracting aspects, we rate expressions by aspect similarity recognition (ASR), which evaluates whethe...

Long Short Term Memory (LSTM) and Convolutional Neural Network (CNN) are efficiently applied to natural language processing, especially sentiment analysis. CNN employs filters to capture local dependencies while LSTM designs a cell to memorize long-distance information. However, integrating these advantages into one model is challenging because of...

Phrase-based machine translation (MT) systems require large bilingual corpora for training. Nevertheless, such large bilingual corpora are unavailable for most language pairs in the world, causing a bottleneck for the development of MT. For the Asian language pairs—Japanese, Indonesian, Malay paired with Vietnamese—they are also not excluded from t...

We present our method for tackling the legal case retrieval task of the Competition on Legal Information Extraction/Entailment 2019. Our approach is based on the idea that summarization is important for retrieval. On one hand, we adopt a summarization based model called encoded summarization which encodes a given document into continuous vector spa...

Among the six challenges of neural machine translation (NMT) coined by \cite{Koehn2017}, rare-word problem is considered the most severe one, especially in translation of low-resource languages. In this paper, we propose three solutions to address the rare words in neural machine translation systems. First, we enhance source context to predict the...