Duc-Vu Nguyen

Vu-Thuan Doan, Quoc-Truong Truong, Duc-Vu Nguyen et al.

Large language models (LLMs), such as GPT-4, PaLM, and LLaMa, have been shown to achieve remarkable performance across a variety of natural language tasks. Recent advancements in instruction tuning bring LLMs with ability in following user's instructions and producing human-like responses. However, the high costs associated with training and implementing LLMs pose challenges to academic research. Furthermore, the availability of pretrained LLMs and instruction-tune datasets for Vietnamese language is limited. To tackle these concerns, we leverage large-scale instruction-following datasets from open-source projects, namely Alpaca, GPT4All, and Chat-Doctor, which cover general domain and specific medical domain. To the best of our knowledge, these are the first instructional dataset for Vietnamese. Subsequently, we utilize parameter-efficient tuning through Low-Rank Adaptation (LoRA) on two open LLMs: Bloomz (Multilingual) and GPTJ-6B (Vietnamese), resulting four models: Bloomz-Chat, Bloomz-Doctor, GPTJ-Chat, GPTJ-Doctor.Finally, we assess the effectiveness of our methodology on a per-sample basis, taking into consideration the helpfulness, relevance, accuracy, level of detail in their responses. This evaluation process entails the utilization of GPT-4 as an automated scoring mechanism. Despite utilizing a low-cost setup, our method demonstrates about 20-30\% improvement over the original models in our evaluation tasks.

Quoc-Nam Nguyen, Thang Chau Phan, Duc-Vu Nguyen et al.

English and Chinese, known as resource-rich languages, have witnessed the strong development of transformer-based language models for natural language processing tasks. Although Vietnam has approximately 100M people speaking Vietnamese, several pre-trained models, e.g., PhoBERT, ViBERT, and vELECTRA, performed well on general Vietnamese NLP tasks, including POS tagging and named entity recognition. These pre-trained language models are still limited to Vietnamese social media tasks. In this paper, we present the first monolingual pre-trained language model for Vietnamese social media texts, ViSoBERT, which is pre-trained on a large-scale corpus of high-quality and diverse Vietnamese social media texts using XLM-R architecture. Moreover, we explored our pre-trained model on five important natural language downstream tasks on Vietnamese social media texts: emotion recognition, hate speech detection, sentiment analysis, spam reviews detection, and hate speech spans detection. Our experiments demonstrate that ViSoBERT, with far fewer parameters, surpasses the previous state-of-the-art models on multiple Vietnamese social media tasks. Our ViSoBERT model is available only for research purposes.

Hang Thi-Thu Le, Viet-Duc Ho, Duc-Vu Nguyen et al.

Machine Reading Comprehension has become one of the most advanced and popular research topics in the fields of Natural Language Processing in recent years. The classification of answerability questions is a relatively significant sub-task in machine reading comprehension; however, there haven't been many studies. Retro-Reader is one of the studies that has solved this problem effectively. However, the encoders of most traditional machine reading comprehension models in general and Retro-Reader, in particular, have not been able to exploit the contextual semantic information of the context completely. Inspired by SemBERT, we use semantic role labels from the SRL task to add semantics to pre-trained language models such as mBERT, XLM-R, PhoBERT. This experiment was conducted to compare the influence of semantics on the classification of answerability for the Vietnamese machine reading comprehension. Additionally, we hope this experiment will enhance the encoder for the Retro-Reader model's Sketchy Reading Module. The improved Retro-Reader model's encoder with semantics was first applied to the Vietnamese Machine Reading Comprehension task and obtained positive results.

Quoc-Loc Duong, Duc-Vu Nguyen, Ngan Luu-Thuy Nguyen

RTE is a significant problem and is a reasonably active research community. The proposed research works on the approach to this problem are pretty diverse with many different directions. For Vietnamese, the RTE problem is moderately new, but this problem plays a vital role in natural language understanding systems. Currently, methods to solve this problem based on contextual word representation learning models have given outstanding results. However, Vietnamese is a semantically rich language. Therefore, in this paper, we want to present an experiment combining semantic word representation through the SRL task with context representation of BERT relative models for the RTE problem. The experimental results give conclusions about the influence and role of semantic representation on Vietnamese in understanding natural language. The experimental results show that the semantic-aware contextual representation model has about 1% higher performance than the model that does not incorporate semantic representation. In addition, the effects on the data domain in Vietnamese are also higher than those in English. This result also shows the positive influence of SRL on RTE problem in Vietnamese.

Duc-Vu Nguyen, Quoc-Nam Nguyen

In this paper, we evaluate the ability of large language models (LLMs) to perform multiple choice symbol binding (MCSB) for multiple choice question answering (MCQA) tasks in zero-shot, one-shot, and few-shot settings. We focus on Vietnamese, with fewer challenging MCQA datasets than in English. The two existing datasets, ViMMRC 1.0 and ViMMRC 2.0, focus on literature. Recent research in Vietnamese natural language processing (NLP) has focused on the Vietnamese National High School Graduation Examination (VNHSGE) from 2019 to 2023 to evaluate ChatGPT. However, these studies have mainly focused on how ChatGPT solves the VNHSGE step by step. We aim to create a novel and high-quality dataset by providing structured guidelines for typing LaTeX formulas for mathematics, physics, chemistry, and biology. This dataset can be used to evaluate the MCSB ability of LLMs and smaller language models (LMs) because it is typed in a strict LaTeX style. We focus on predicting the character (A, B, C, or D) that is the most likely answer to a question, given the context of the question. Our evaluation of six well-known LLMs, namely BLOOMZ-7.1B-MT, LLaMA-2-7B, LLaMA-2-70B, GPT-3, GPT-3.5, and GPT-4.0, on the ViMMRC 1.0 and ViMMRC 2.0 benchmarks and our proposed dataset shows promising results on the MCSB ability of LLMs for Vietnamese. The dataset is available for research purposes only.

Duc-Vu Nguyen, Ngan Luu-Thuy Nguyen

To the best of our knowledge, this paper made the first attempt to answer whether word segmentation is necessary for Vietnamese sentiment classification. To do this, we presented five pre-trained monolingual S4- based language models for Vietnamese, including one model without word segmentation, and four models using RDRsegmenter, uitnlp, pyvi, or underthesea toolkits in the pre-processing data phase. According to comprehensive experimental results on two corpora, including the VLSP2016-SA corpus of technical article reviews from the news and social media and the UIT-VSFC corpus of the educational survey, we have two suggestions. Firstly, using traditional classifiers like Naive Bayes or Support Vector Machines, word segmentation maybe not be necessary for the Vietnamese sentiment classification corpus, which comes from the social domain. Secondly, word segmentation is necessary for Vietnamese sentiment classification when word segmentation is used before using the BPE method and feeding into the deep learning model. In this way, the RDRsegmenter is the stable toolkit for word segmentation among the uitnlp, pyvi, and underthesea toolkits.

Trung Tien Cao, Lam Minh Thai, Nghia Hieu Nguyen et al.

Multiple-choice Reading Comprehension (MCRC) models aim to select the correct answer from a set of candidate options for a given question. However, they typically lack the ability to explain the reasoning behind their choices. In this paper, we introduce a novel Vietnamese dataset designed to train and evaluate MCRC models with explanation generation capabilities. Furthermore, we propose ViMultiChoice, a new method specifically designed for modeling Vietnamese reading comprehension that jointly predicts the correct answer and generates a corresponding explanation. Experimental results demonstrate that ViMultiChoice outperforms existing MCRC baselines, achieving state-of-the-art (SotA) performance on both the ViMMRC 2.0 benchmark and the newly introduced dataset. Additionally, we show that jointly training option decision and explanation generation leads to significant improvements in multiple-choice accuracy.

Kim Thi-Thanh Nguyen, Sieu Khai Huynh, Luong Luc Phan et al.

Aspect-based sentiment analysis plays an essential role in natural language processing and artificial intelligence. Recently, researchers only focused on aspect detection and sentiment classification but ignoring the sub-task of detecting user opinion span, which has enormous potential in practical applications. In this paper, we present a new Vietnamese dataset (UIT-ViSD4SA) consisting of 35,396 human-annotated spans on 11,122 feedback comments for evaluating the span detection in aspect-based sentiment analysis. Besides, we also propose a novel system using Bidirectional Long Short-Term Memory (BiLSTM) with a Conditional Random Field (CRF) layer (BiLSTM-CRF) for the span detection task in Vietnamese aspect-based sentiment analysis. The best result is a 62.76% F1 score (macro) for span detection using BiLSTM-CRF with embedding fusion of syllable embedding, character embedding, and contextual embedding from XLM-RoBERTa. In future work, span detection will be extended in many NLP tasks such as constructive detection, emotion recognition, complaint analysis, and opinion mining. Our dataset is freely available at https://github.com/kimkim00/UIT-ViSD4SA for research purposes.

Hieu-Dai Tran, Duc-Vu Nguyen, Ngan Luu-Thuy Nguyen

Coreference resolution is a vital task in natural language processing (NLP) that involves identifying and linking different expressions in a text that refer to the same entity. This task is particularly challenging for Vietnamese, a low-resource language with limited annotated datasets. To address these challenges, we developed a comprehensive annotated dataset using narrative texts from VnExpress, a widely-read Vietnamese online news platform. We established detailed guidelines for annotating entities, focusing on ensuring consistency and accuracy. Additionally, we evaluated the performance of large language models (LLMs), specifically GPT-3.5-Turbo and GPT-4, on this dataset. Our results demonstrate that GPT-4 significantly outperforms GPT-3.5-Turbo in terms of both accuracy and response consistency, making it a more reliable tool for coreference resolution in Vietnamese.

Duc-Vu Nguyen, Thang Chau Phan, Quoc-Nam Nguyen et al.

In this paper, we aimed to develop a neural parser for Vietnamese based on simplified Head-Driven Phrase Structure Grammar (HPSG). The existing corpora, VietTreebank and VnDT, had around 15% of constituency and dependency tree pairs that did not adhere to simplified HPSG rules. To attempt to address the issue of the corpora not adhering to simplified HPSG rules, we randomly permuted samples from the training and development sets to make them compliant with simplified HPSG. We then modified the first simplified HPSG Neural Parser for the Penn Treebank by replacing it with the PhoBERT or XLM-RoBERTa models, which can encode Vietnamese texts. We conducted experiments on our modified VietTreebank and VnDT corpora. Our extensive experiments showed that the simplified HPSG Neural Parser achieved a new state-of-the-art F-score of 82% for constituency parsing when using the same predicted part-of-speech (POS) tags as the self-attentive constituency parser. Additionally, it outperformed previous studies in dependency parsing with a higher Unlabeled Attachment Score (UAS). However, our parser obtained lower Labeled Attachment Score (LAS) scores likely due to our focus on arc permutation without changing the original labels, as we did not consult with a linguistic expert. Lastly, the research findings of this paper suggest that simplified HPSG should be given more attention to linguistic expert when developing treebanks for Vietnamese natural language processing.

Trong-Thuan Nguyen, Viet-Tham Huynh, Quang-Thuc Nguyen et al.

Recent 3D retrieval systems are typically designed for simple, controlled scenarios, such as identifying an object from a cropped image or a brief description. However, real-world scenarios are more complex, often requiring the recognition of an object in a cluttered scene based on a vague, free-form description. To this end, we present ROOMELSA, a new benchmark designed to evaluate a system's ability to interpret natural language. Specifically, ROOMELSA attends to a specific region within a panoramic room image and accurately retrieves the corresponding 3D model from a large database. In addition, ROOMELSA includes over 1,600 apartment scenes, nearly 5,200 rooms, and more than 44,000 targeted queries. Empirically, while coarse object retrieval is largely solved, only one top-performing model consistently ranked the correct match first across nearly all test cases. Notably, a lightweight CLIP-based model also performed well, although it struggled with subtle variations in materials, part structures, and contextual cues, resulting in occasional errors. These findings highlight the importance of tightly integrating visual and language understanding. By bridging the gap between scene-level grounding and fine-grained 3D retrieval, ROOMELSA establishes a new benchmark for advancing robust, real-world 3D recognition systems.

Van-Hoang Le, Duc-Vu Nguyen, Kiet Van Nguyen et al.

Large Language Models (LLMs) face significant challenges in specialized domains like law, where precision and domain-specific knowledge are critical. This paper presents a streamlined two-stage framework consisting of Retrieval and Re-ranking to enhance legal document retrieval efficiency and accuracy. Our approach employs a fine-tuned Bi-Encoder for rapid candidate retrieval, followed by a Cross-Encoder for precise re-ranking, both optimized through strategic negative example mining. Key innovations include the introduction of the Exist@m metric to evaluate retrieval effectiveness and the use of semi-hard negatives to mitigate training bias, which significantly improved re-ranking performance. Evaluated on the SoICT Hackathon 2024 for Legal Document Retrieval, our team, 4Huiter, achieved a top-three position. While top-performing teams employed ensemble models and iterative self-training on large bge-m3 architectures, our lightweight, single-pass approach offered a competitive alternative with far fewer parameters. The framework demonstrates that optimized data processing, tailored loss functions, and balanced negative sampling are pivotal for building robust retrieval-augmented systems in legal contexts.

Nhu-Thanh Nguyen, Khoa Thi-Kim Phan, Duc-Vu Nguyen et al.

Abuse in its various forms, including physical, psychological, verbal, sexual, financial, and cultural, has a negative impact on mental health. However, there are limited studies on applying natural language processing (NLP) in this field in Vietnam. Therefore, we aim to contribute by building a human-annotated Vietnamese dataset for detecting abusive content in Vietnamese narrative texts. We sourced these texts from VnExpress, Vietnam's popular online newspaper, where readers often share stories containing abusive content. Identifying and categorizing abusive spans in these texts posed significant challenges during dataset creation, but it also motivated our research. We experimented with lightweight baseline models by freezing PhoBERT and XLM-RoBERTa and using their hidden states in a BiLSTM to assess the complexity of the dataset. According to our experimental results, PhoBERT outperforms other models in both labeled and unlabeled abusive span detection tasks. These results indicate that it has the potential for future improvements.

Duc-Vu Nguyen, Linh-Bao Vo, Ngoc-Linh Tran et al.

Chinese word segmentation and part-of-speech tagging are necessary tasks in terms of computational linguistics and application of natural language processing. Many re-searchers still debate the demand for Chinese word segmentation and part-of-speech tagging in the deep learning era. Nevertheless, resolving ambiguities and detecting unknown words are challenging problems in this field. Previous studies on joint Chinese word segmentation and part-of-speech tagging mainly follow the character-based tagging model focusing on modeling n-gram features. Unlike previous works, we propose a neural model named SpanSegTag for joint Chinese word segmentation and part-of-speech tagging following the span labeling in which the probability of each n-gram being the word and the part-of-speech tag is the main problem. We use the biaffine operation over the left and right boundary representations of consecutive characters to model the n-grams. Our experiments show that our BERT-based model SpanSegTag achieved competitive performances on the CTB5, CTB6, and UD, or significant improvements on CTB7 and CTB9 benchmark datasets compared with the current state-of-the-art method using BERT or ZEN encoders.

Duc-Vu Nguyen, Linh-Bao Vo, Dang Van Thin et al.

In this paper, we propose a span labeling approach to model n-gram information for Vietnamese word segmentation, namely SPAN SEG. We compare the span labeling approach with the conditional random field by using encoders with the same architecture. Since Vietnamese and Chinese have similar linguistic phenomena, we evaluated the proposed method on the Vietnamese treebank benchmark dataset and five Chinese benchmark datasets. Through our experimental results, the proposed approach SpanSeg achieves higher performance than the sequence tagging approach with the state-of-the-art F-score of 98.31% on the Vietnamese treebank benchmark, when they both apply the contextual pre-trained language model XLM-RoBERTa and the predicted word boundary information. Besides, we do fine-tuning experiments for the span labeling approach on BERT and ZEN pre-trained language model for Chinese with fewer parameters, faster inference time, and competitive or higher F-scores than the previous state-of-the-art approach, word segmentation with word-hood memory networks, on five Chinese benchmarks.

Duc-Vu Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen

Word segmentation and part-of-speech tagging are two critical preliminary steps for downstream tasks in Vietnamese natural language processing. In reality, people tend to consider also the phrase boundary when performing word segmentation and part of speech tagging rather than solely process word by word from left to right. In this paper, we implement this idea to improve word segmentation and part of speech tagging the Vietnamese language by employing a simplified constituency parser. Our neural model for joint word segmentation and part-of-speech tagging has the architecture of the syllable-based CRF constituency parser. To reduce the complexity of parsing, we replace all constituent labels with a single label indicating for phrases. This model can be augmented with predicted word boundary and part-of-speech tags by other tools. Because Vietnamese and Chinese have some similar linguistic phenomena, we evaluated the proposed model and its augmented versions on three Vietnamese benchmark datasets and six Chinese benchmark datasets. Our experimental results show that the proposed model achieves higher performances than previous works for both languages.

Tuan-Vi Tran, Xuan-Thien Pham, Duc-Vu Nguyen et al.

In this work, we use a span-based approach for Vietnamese constituency parsing. Our method follows the self-attention encoder architecture and a chart decoder using a CKY-style inference algorithm. We present analyses of the experiment results of the comparison of our empirical method using pre-training models XLM-Roberta and PhoBERT on both Vietnamese datasets VietTreebank and NIIVTB1. The results show that our model with XLM-Roberta archived the significantly F1-score better than other pre-training models, VietTreebank at 81.19% and NIIVTB1 at 85.70%.

Kiet Van Nguyen, Duc-Vu Nguyen, Anh Gia-Tuan Nguyen et al.

Over 97 million people speak Vietnamese as their native language in the world. However, there are few research studies on machine reading comprehension (MRC) for Vietnamese, the task of understanding a text and answering questions related to it. Due to the lack of benchmark datasets for Vietnamese, we present the Vietnamese Question Answering Dataset (UIT-ViQuAD), a new dataset for the low-resource language as Vietnamese to evaluate MRC models. This dataset comprises over 23,000 human-generated question-answer pairs based on 5,109 passages of 174 Vietnamese articles from Wikipedia. In particular, we propose a new process of dataset creation for Vietnamese MRC. Our in-depth analyses illustrate that our dataset requires abilities beyond simple reasoning like word matching and demands single-sentence and multiple-sentence inferences. Besides, we conduct experiments on state-of-the-art MRC methods for English and Chinese as the first experimental models on UIT-ViQuAD. We also estimate human performance on the dataset and compare it to the experimental results of powerful machine learning models. As a result, the substantial differences between human performance and the best model performance on the dataset indicate that improvements can be made on UIT-ViQuAD in future research. Our dataset is freely available on our website to encourage the research community to overcome challenges in Vietnamese MRC.

Kiet Van Nguyen, Tin Van Huynh, Duc-Vu Nguyen et al.

Large-scale and high-quality corpora are necessary for evaluating machine reading comprehension models on a low-resource language like Vietnamese. Besides, machine reading comprehension (MRC) for the health domain offers great potential for practical applications; however, there is still very little MRC research in this domain. This paper presents ViNewsQA as a new corpus for the Vietnamese language to evaluate healthcare reading comprehension models. The corpus comprises 22,057 human-generated question-answer pairs. Crowd-workers create the questions and their answers based on a collection of over 4,416 online Vietnamese healthcare news articles, where the answers comprise spans extracted from the corresponding articles. In particular, we develop a process of creating a corpus for the Vietnamese machine reading comprehension. Comprehensive evaluations demonstrate that our corpus requires abilities beyond simple reasoning, such as word matching and demanding difficult reasoning based on single-or-multiple-sentence information. We conduct experiments using different types of machine reading comprehension methods to achieve the first baseline performances, compared with further models' performances. We also measure human performance on the corpus and compared it with several powerful neural network-based and transfer learning-based models. Our experiments show that the best machine model is ALBERT, which achieves an exact match score of 65.26% and an F1-score of 84.89% on our corpus. The significant differences between humans and the best-performance model (14.53% of EM and 10.90% of F1-score) on the test set of our corpus indicate that improvements in ViNewsQA could be explored in the future study. Our corpus is publicly available on our website for the research purpose to encourage the research community to make these improvements.

Duc-Vu Nguyen, Dang Van Thin, Kiet Van Nguyen et al.

In this paper, we approach Vietnamese word segmentation as a binary classification by using the Support Vector Machine classifier. We inherit features from prior works such as n-gram of syllables, n-gram of syllable types, and checking conjunction of adjacent syllables in the dictionary. We propose two novel ways to feature extraction, one to reduce the overlap ambiguity and the other to increase the ability to predict unknown words containing suffixes. Different from UETsegmenter and RDRsegmenter, two state-of-the-art Vietnamese word segmentation methods, we do not employ the longest matching algorithm as an initial processing step or any post-processing technique. According to experimental results on benchmark Vietnamese datasets, our proposed method obtained a better F1-score than the prior state-of-the-art methods UETsegmenter, and RDRsegmenter.

Vong Anh Ho, Duong Huynh-Cong Nguyen, Danh Hoang Nguyen et al.

Emotion recognition or emotion prediction is a higher approach or a special case of sentiment analysis. In this task, the result is not produced in terms of either polarity: positive or negative or in the form of rating (from 1 to 5) but of a more detailed level of analysis in which the results are depicted in more expressions like sadness, enjoyment, anger, disgust, fear, and surprise. Emotion recognition plays a critical role in measuring the brand value of a product by recognizing specific emotions of customers' comments. In this study, we have achieved two targets. First and foremost, we built a standard Vietnamese Social Media Emotion Corpus (UIT-VSMEC) with exactly 6,927 emotion-annotated sentences, contributing to emotion recognition research in Vietnamese which is a low-resource language in natural language processing (NLP). Secondly, we assessed and measured machine learning and deep neural network models on our UIT-VSMEC corpus. As a result, the CNN model achieved the highest performance with the weighted F1-score of 59.74%. Our corpus is available at our research website.