Long Hoang Nguyen

Shruti Bhargava, Anand Dhoot, Ing-Marie Jonsson et al.

Voice assistants help users make phone calls, send messages, create events, navigate, and do a lot more. However, assistants have limited capacity to understand their users' context. In this work, we aim to take a step in this direction. Our work dives into a new experience for users to refer to phone numbers, addresses, email addresses, URLs, and dates on their phone screens. Our focus lies in reference understanding, which becomes particularly interesting when multiple similar texts are present on screen, similar to visual grounding. We collect a dataset and propose a lightweight general-purpose model for this novel experience. Due to the high cost of consuming pixels directly, our system is designed to rely on the extracted text from the UI. Our model is modular, thus offering flexibility, improved interpretability, and efficient runtime memory utilization.

Thanh Tin Nguyen, Long H. Nguyen, Nhat Truong Pham et al.

This study presents our approach on the automatic Vietnamese image captioning for healthcare domain in text processing tasks of Vietnamese Language and Speech Processing (VLSP) Challenge 2021, as shown in Figure 1. In recent years, image captioning often employs a convolutional neural network-based architecture as an encoder and a long short-term memory (LSTM) as a decoder to generate sentences. These models perform remarkably well in different datasets. Our proposed model also has an encoder and a decoder, but we instead use a Swin Transformer in the encoder, and a LSTM combined with an attention module in the decoder. The study presents our training experiments and techniques used during the competition. Our model achieves a BLEU4 score of 0.293 on the vietCap4H dataset, and the score is ranked the 3$^{rd}$ place on the private leaderboard. Our code can be found at \url{https://git.io/JDdJm}.

Viet H. Pham, Thang M. Pham, Giang Nguyen et al.

The advent of deep learning has led to a significant gain in machine translation. However, most of the studies required a large parallel dataset which is scarce and expensive to construct and even unavailable for some languages. This paper presents a simple yet effective method to tackle this problem for low-resource languages by augmenting high-quality sentence pairs and training NMT models in a semi-supervised manner. Specifically, our approach combines the cross-entropy loss for supervised learning with KL Divergence for unsupervised fashion given pseudo and augmented target sentences derived from the model. We also introduce a SentenceBERT-based filter to enhance the quality of augmenting data by retaining semantically similar sentence pairs. Experimental results show that our approach significantly improves NMT baselines, especially on low-resource datasets with 0.46--2.03 BLEU scores. We also demonstrate that using unsupervised training for augmented data is more efficient than reusing the ground-truth target sentences for supervised learning.

Minh Duong, Long Nguyen, Yen Vuong et al.

This paper presents a deep learning-based system for efficient automatic case summarization. Leveraging state-of-the-art natural language processing techniques, the system offers both supervised and unsupervised methods to generate concise and relevant summaries of lengthy legal case documents. The user-friendly interface allows users to browse the system's database of legal case documents, select their desired case, and choose their preferred summarization method. The system generates comprehensive summaries for each subsection of the legal text as well as an overall summary. This demo streamlines legal case document analysis, potentially benefiting legal professionals by reducing workload and increasing efficiency. Future work will focus on refining summarization techniques and exploring the application of our methods to other types of legal texts.

Long H. Nguyen, Nhat Truong Pham, Van Huong Do et al.

SARS-CoV-2 is colloquially known as COVID-19 that had an initial outbreak in December 2019. The deadly virus has spread across the world, taking part in the global pandemic disease since March 2020. In addition, a recent variant of SARS-CoV-2 named Delta is intractably contagious and responsible for more than four million deaths over the world. Therefore, it is vital to possess a self-testing service of SARS-CoV-2 at home. In this study, we introduce Fruit-CoV, a two-stage vision framework, which is capable of detecting SARS-CoV-2 infections through recorded cough sounds. Specifically, we convert sounds into Log-Mel Spectrograms and use the EfficientNet-V2 network to extract its visual features in the first stage. In the second stage, we use 14 convolutional layers extracted from the large-scale Pretrained Audio Neural Networks for audio pattern recognition (PANNs) and the Wavegram-Log-Mel-CNN to aggregate feature representations of the Log-Mel Spectrograms. Finally, we use the combined features to train a binary classifier. In this study, we use a dataset provided by the AICovidVN 115M Challenge, which includes a total of 7371 recorded cough sounds collected throughout Vietnam, India, and Switzerland. Experimental results show that our proposed model achieves an AUC score of 92.8% and ranks the 1st place on the leaderboard of the AICovidVN Challenge. More importantly, our proposed framework can be integrated into a call center or a VoIP system to speed up detecting SARS-CoV-2 infections through online/recorded cough sounds.

Hoang Long Nguyen, Vincent Renkens, Joris Pelemans et al.

Recognition errors are common in human communication. Similar errors often lead to unwanted behaviour in dialogue systems or virtual assistants. In human communication, we can recover from them by repeating misrecognized words or phrases; however in human-machine communication this recovery mechanism is not available. In this paper, we attempt to bridge this gap and present a system that allows a user to correct speech recognition errors in a virtual assistant by repeating misunderstood words. When a user repeats part of the phrase the system rewrites the original query to incorporate the correction. This rewrite allows the virtual assistant to understand the original query successfully. We present an end-to-end 2-step attention pointer network that can generate the the rewritten query by merging together the incorrectly understood utterance with the correction follow-up. We evaluate the model on data collected for this task and compare the proposed model to a rule-based baseline and a standard pointer network. We show that rewriting the original query is an effective way to handle repetition-based recovery and that the proposed model outperforms the rule based baseline, reducing Word Error Rate by 19% relative at 2% False Alarm Rate on annotated data.

Hoang Long Nguyen, Zhenhe Pan, Hashim Abu-gellban et al.

The World Health Organization (WHO) announced that COVID-19 was a pandemic disease on the 11th of March as there were 118K cases in several countries and territories. Numerous researchers worked on forecasting the number of confirmed cases since anticipating the growth of the cases helps governments adopting knotty decisions to ease the lockdowns orders for their countries. These orders help several people who have lost their jobs and support gravely impacted businesses. Our research aims to investigate the relation between Google search trends and the spreading of the novel coronavirus (COVID-19) over countries worldwide, to predict the number of cases. We perform a correlation analysis on the keywords of the related Google search trends according to the number of confirmed cases reported by the WHO. After that, we applied several machine learning techniques (Multiple Linear Regression, Non-negative Integer Regression, Deep Neural Network), to forecast the number of confirmed cases globally based on historical data as well as the hybrid data (Google search trends). Our results show that Google search trends are highly associated with the number of reported confirmed cases, where the Deep Learning approach outperforms other forecasting techniques. We believe that it is not only a promising approach for forecasting the confirmed cases of COVID-19, but also for similar forecasting problems that are associated with the related Google trends.

Long H. Nguyen, Zhenhe Pan, Opeyemi Openiyi et al.

A robust model for time series forecasting is highly important in many domains, including but not limited to financial forecast, air temperature and electricity consumption. To improve forecasting performance, traditional approaches usually require additional feature sets. However, adding more feature sets from different sources of data is not always feasible due to its accessibility limitation. In this paper, we propose a novel self-boosted mechanism in which the original time series is decomposed into multiple time series. These time series played the role of additional features in which the closely related time series group is used to feed into multi-task learning model, and the loosely related group is fed into multi-view learning part to utilize its complementary information. We use three real-world datasets to validate our model and show the superiority of our proposed method over existing state-of-the-art baseline methods.

L. H. Nguyen, N. T. H. Pham, V. M. Ngo

Nowadays, there are a lot of people using social media opinions to make their decision on buying products or services. Opinion spam detection is a hard problem because fake reviews can be made by organizations as well as individuals for different purposes. They write fake reviews to mislead readers or automated detection system by promoting or demoting target products to promote them or to damage their reputations. In this paper, we pro-pose a new approach using knowledge-based Ontology to detect opinion spam with high accuracy (higher than 75%). Keywords: Opinion spam, Fake review, E-commercial, Ontology.

Jan Pichl, Petr Marek, Jakub Konrád et al.

This paper describes a new open domain dialogue system Alquist developed as part of the Alexa Prize competition for the Amazon Echo line of products. The Alquist dialogue system is designed to conduct a coherent and engaging conversation on popular topics. We are presenting a hybrid system combining several machine learning and rule based approaches. We discuss and describe the Alquist pipeline, data acquisition, and processing, dialogue manager, NLG, knowledge aggregation and hierarchy of sub-dialogs. We present some of the experimental results.