Search

This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2022: low-resource and dialect speech translation. For the Tunisian Arabic-English dataset (low-resource and dialect tracks), we build an end-to-end model as our joint primary submission, and compare it against cascaded models that leverage a large fine-tuned wav2vec 2.0 model for ASR. Our results show that in our settings pipeline approaches are still very competitive, and that with the use of transfer learning, they can outperform end-to-end models for speech translation (ST). For the Tamasheq-French dataset (low-resource track) our primary submission leverages intermediate representations from a wav2vec 2.0 model trained on 234 hours of Tamasheq audio, while our contrastive model uses a French phonetic transcription of the Tamasheq audio as input in a Conformer speech translation architecture jointly trained on automatic speech recognition, ST and machine translation losses. Our results highlight that self-supervised models trained on smaller sets of target data are more effective to low-resource end-to-end ST fine-tuning, compared to large off-the-shelf models. Results also illustrate that even approximate phonetic transcriptions can improve ST scores., Comment: IWSLT 2022 system paper

We summarize the evaluation of the first Automated Legal Question Answering Competition (ALQAC 2021). The competition this year contains three tasks, which aims at processing the statute law document, which are Legal Text Information Retrieval (Task 1), Legal Text Entailment Prediction (Task 2), and Legal Text Question Answering (Task 3). The final goal of these tasks is to build a system that can automatically determine whether a particular statement is lawful. There is no limit to the approaches of the participating teams. This year, there are 5 teams participating in Task 1, 6 teams participating in Task 2, and 5 teams participating in Task 3. There are in total 36 runs submitted to the organizer. In this paper, we summarize each team's approaches, official results, and some discussion about the competition. Only results of the teams who successfully submit their approach description paper are reported in this paper.

The development of diagnostic models for detecting and diagnosing pediatric diseases in CXR scans is undertaken due to the lack of high-quality physician-annotated datasets. To overcome this challenge, we introduce and release PediCXR, a new pediatric CXR dataset of 9,125 studies retrospectively collected from a major pediatric hospital in Vietnam between 2020 and 2021. Each scan was manually annotated by a pediatric radiologist with more than ten years of experience. The dataset was labeled for the presence of 36 critical findings and 15 diseases. In particular, each abnormal finding was identified via a rectangle bounding box on the image. To the best of our knowledge, this is the first and largest pediatric CXR dataset containing lesion-level annotations and image-level labels for the detection of multiple findings and diseases. For algorithm development, the dataset was divided into a training set of 7,728 and a test set of 1,397. To encourage new advances in pediatric CXR interpretation using data-driven approaches, we provide a detailed description of the PediCXR data sample and make the dataset publicly available on https://physionet.org/content/pedicxr/1.0.0/, Comment: Accepted by Scientific Data (Nature). arXiv admin note: text overlap with arXiv:2012.15029

Building an accurate computer-aided diagnosis system based on data-driven approaches requires a large amount of high-quality labeled data. In medical imaging analysis, multiple expert annotators often produce subjective estimates about "ground truth labels" during the annotation process, depending on their expertise and experience. As a result, the labeled data may contain a variety of human biases with a high rate of disagreement among annotators, which significantly affect the performance of supervised machine learning algorithms. To tackle this challenge, we propose a simple yet effective approach to combine annotations from multiple radiology experts for training a deep learning-based detector that aims to detect abnormalities on medical scans. The proposed method first estimates the ground truth annotations and confidence scores of training examples. The estimated annotations and their scores are then used to train a deep learning detector with a re-weighted loss function to localize abnormal findings. We conduct an extensive experimental evaluation of the proposed approach on both simulated and real-world medical imaging datasets. The experimental results show that our approach significantly outperforms baseline approaches that do not consider the disagreements among annotators, including methods in which all of the noisy annotations are treated equally as ground truth and the ensemble of different models trained on different label sets provided separately by annotators., Comment: Under review by Neurocomputing

Image augmentation techniques have been widely investigated to improve the performance of deep learning (DL) algorithms on mammography classification tasks. Recent methods have proved the efficiency of image augmentation on data deficiency or data imbalance issues. In this paper, we propose a novel transparency strategy to boost the Breast Imaging Reporting and Data System (BI-RADS) scores of mammogram classifiers. The proposed approach utilizes the Region of Interest (ROI) information to generate more high-risk training examples for breast cancer (BI-RADS 3, 4, 5) from original images. Our extensive experiments on three different datasets show that the proposed approach significantly improves the mammogram classification performance and surpasses a state-of-the-art data augmentation technique called CutMix. This study also highlights that our transparency method is more effective than other augmentation strategies for BI-RADS classification and can be widely applied to other computer vision tasks., Comment: Accepted for presentation at the 22nd IEEE Statistical Signal Processing (SSP) workshop

A fully automated system for interpreting abdominal computed tomography (CT) scans with multiple phases of contrast enhancement requires an accurate classification of the phases. This work aims at developing and validating a precise, fast multi-phase classifier to recognize three main types of contrast phases in abdominal CT scans. We propose in this study a novel method that uses a random sampling mechanism on top of deep CNNs for the phase recognition of abdominal CT scans of four different phases: non-contrast, arterial, venous, and others. The CNNs work as a slice-wise phase prediction, while the random sampling selects input slices for the CNN models. Afterward, majority voting synthesizes the slice-wise results of the CNNs, to provide the final prediction at scan level. Our classifier was trained on 271,426 slices from 830 phase-annotated CT scans, and when combined with majority voting on 30% of slices randomly chosen from each scan, achieved a mean F1-score of 92.09% on our internal test set of 358 scans. The proposed method was also evaluated on 2 external test sets: CTPAC-CCRCC (N = 242) and LiTS (N = 131), which were annotated by our experts. Although a drop in performance has been observed, the model performance remained at a high level of accuracy with a mean F1-score of 76.79% and 86.94% on CTPAC-CCRCC and LiTS datasets, respectively. Our experimental results also showed that the proposed method significantly outperformed the state-of-the-art 3D approaches while requiring less computation time for inference., Comment: Accepted for publication by Medical Physics

Mammography, or breast X-ray, is the most widely used imaging modality to detect cancer and other breast diseases. Recent studies have shown that deep learning-based computer-assisted detection and diagnosis (CADe or CADx) tools have been developed to support physicians and improve the accuracy of interpreting mammography. However, most published datasets of mammography are either limited on sample size or digitalized from screen-film mammography (SFM), hindering the development of CADe and CADx tools which are developed based on full-field digital mammography (FFDM). To overcome this challenge, we introduce VinDr-Mammo - a new benchmark dataset of FFDM for detecting and diagnosing breast cancer and other diseases in mammography. The dataset consists of 5,000 mammography exams, each of which has four standard views and is double read with disagreement (if any) being resolved by arbitration. It is created for the assessment of Breast Imaging Reporting and Data System (BI-RADS) and density at the breast level. In addition, the dataset also provides the category, location, and BI-RADS assessment of non-benign findings. We make VinDr-Mammo publicly available on PhysioNet as a new imaging resource to promote advances in developing CADe and CADx tools for breast cancer screening., Comment: The manuscript is accepted for publication by Scientific Data (Nature)

In recent years, thanks to breakthroughs in neural network techniques especially attentive deep learning models, natural language processing has made many impressive achievements. However, automated legal word processing is still a difficult branch of natural language processing. Legal sentences are often long and contain complicated legal terminologies. Hence, models that work well on general documents still face challenges in dealing with legal documents. We have verified the existence of this problem with our experiments in this work. In this dissertation, we selectively present the main achievements in improving attentive neural networks in automatic legal document processing. Language models tend to grow larger and larger, though, without expert knowledge, these models can still fail in domain adaptation, especially for specialized fields like law., Comment: Doctoral Dissertation

Exceptional points (EPs), singularities of non-Hermitian physics where complex spectral resonances degenerate, are one of the most exotic features of nonequilibrium open systems with unique properties. For instance, the emission rate of quantum emitters placed near resonators with EPs is enhanced (compared to the free-space emission rate) by a factor that scales quadratically with the resonance quality factor. Here, we verify the theory of spontaneous emission at EPs by measuring photoluminescence from photonic-crystal slabs that are embedded with a high-quantum-yield active material. While our experimental results verify the theoretically predicted enhancement, it also highlights the practical limitations on the enhancement due to material loss. Our designed structures can be used in applications that require enhanced and controlled emission, such as quantum sensing and imaging.

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 experiments, we found that Transformer-based pretrained language models can perform well with automated legal text processing problems with appropriate approaches. We describe in detail the processing steps for each task such as problem formulation, data processing and augmentation, pretraining, finetuning. In addition, we introduce to the community two pretrained models that take advantage of parallel translations in legal domain, NFSP and NMSP. In which, NFSP achieves the state-of-the-art result in Task 5 of the competition. Although the paper focuses on technical reporting, the novelty of its approaches can also be an useful reference in automated legal document processing using Transformer-based models., Comment: arXiv admin note: substantial text overlap with arXiv:2106.13405

Capturing and faithfully rendering photo-realistic humans from novel views is a fundamental problem for AR/VR applications. While prior work has shown impressive performance capture results in laboratory settings, it is non-trivial to achieve casual free-viewpoint human capture and rendering for unseen identities with high fidelity, especially for facial expressions, hands, and clothes. To tackle these challenges we introduce a novel view synthesis framework that generates realistic renders from unseen views of any human captured from a single-view and sparse RGB-D sensor, similar to a low-cost depth camera, and without actor-specific models. We propose an architecture to create dense feature maps in novel views obtained by sphere-based neural rendering, and create complete renders using a global context inpainting model. Additionally, an enhancer network leverages the overall fidelity, even in occluded areas from the original view, producing crisp renders with fine details. We show that our method generates high-quality novel views of synthetic and real human actors given a single-stream, sparse RGB-D input. It generalizes to unseen identities, and new poses and faithfully reconstructs facial expressions. Our approach outperforms prior view synthesis methods and is robust to different levels of depth sparsity., Comment: Accepted at ECCV 2022, Project page: https://www.phongnhhn.info/HVS_Net/index.html

This paper studies RIS-aided cell-free massive MIMO systems, where multiple RISs are deployed to assist the communication between multiple access points (APs) and multiple users, with either continuous or discrete phase shifts at the RISs. We formulate the max-min fairness problem that maximizes the minimum achievable rate among all users by jointly optimizing the transmit beamforming at active APs and the phase shifts at passive RISs, subject to power constraints at the APs. To address such a challenging problem, we first study the special single-user scenario and propose an algorithm that can transform the optimization problem into semidefinite program (SDP) or integer linear program (ILP) for the cases of continuous and discrete phase shifts, respectively. By solving the resulting SDP and ILP, we first obtain the optimal phase shifts, and then design the optimal transmit beamforming accordingly. To solve the optimization problem for the multi-user scenario and continuous phase shifts at RISs, we extend the single-user algorithm and propose an alternating optimization algorithm, which can first decompose the max-min fairness problem into two subproblems related to transmit beamforming and phase shifts, and then transform the two subproblems into second-order-cone program and SDP, respectively. For the multi-user scenario and discrete phase shifts, the max-min fairness problem is shown to be a mixed-integer non-linear program (MINLP). To tackle it, we design a ZF-based successive refinement algorithm, which can find a suboptimal transmit beamforming and phase shifts by means of alternating optimization. Numerical results show that compared with benchmark schemes of random phase shifts and without using RISs, the proposed algorithms can significantly increase the minimum achievable rate among all users, especially when the number of reflecting elements at each RIS is large., Comment: 13 pages, 10 figures. Submitted to IEEE for possible publication

Advanced deep learning (DL) algorithms may predict the patient's risk of developing breast cancer based on the Breast Imaging Reporting and Data System (BI-RADS) and density standards. Recent studies have suggested that the combination of multi-view analysis improved the overall breast exam classification. In this paper, we propose a novel multi-view DL approach for BI-RADS and density assessment of mammograms. The proposed approach first deploys deep convolutional networks for feature extraction on each view separately. The extracted features are then stacked and fed into a Light Gradient Boosting Machine (LightGBM) classifier to predict BI-RADS and density scores. We conduct extensive experiments on both the internal mammography dataset and the public dataset Digital Database for Screening Mammography (DDSM). The experimental results demonstrate that the proposed approach outperforms the single-view classification approach on two benchmark datasets by huge F1-score margins (+5% on the internal dataset and +10% on the DDSM dataset). These results highlight the vital role of combining multi-view information to improve the performance of breast cancer risk prediction., Comment: This paper has been accepted by the 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (2022 IEEE EMBC)

Employing unmanned aerial vehicles (UAVs) has attracted growing interests and emerged as the state-of-the-art technology for data collection in Internet-of-Things (IoT) networks. In this paper, with the objective of minimizing the total energy consumption of the UAV-IoT system, we formulate the problem of jointly designing the UAV's trajectory and selecting cluster heads in the IoT network as a constrained combinatorial optimization problem which is classified as NP-hard and challenging to solve. We propose a novel deep reinforcement learning (DRL) with a sequential model strategy that can effectively learn the policy represented by a sequence-to-sequence neural network for the UAV's trajectory design in an unsupervised manner. Through extensive simulations, the obtained results show that the proposed DRL method can find the UAV's trajectory that requires much less energy consumption when compared to other baseline algorithms and achieves close-to-optimal performance. In addition, simulation results show that the trained model by our proposed DRL algorithm has an excellent generalization ability to larger problem sizes without the need to retrain the model., Comment: This paper has been accepted in IEEE IoT-J