The rise of social media has led to the increasing of comments on online forums. However, there still exists some invalid comments which were not informative for users. Moreover, those comments are also quite toxic and harmful to people. In this paper, we create a dataset for classifying constructive and toxic speech detection, named UIT-ViCTSD (Vietnamese Constructive and Toxic Speech Detection dataset) with 10,000 human-annotated comments. For these tasks, we proposed a system for constructive and toxic speech detection with the state-of-the-art transfer learning model in Vietnamese NLP as PhoBERT. With this system, we achieved 78.59% and 59.40% F1-score for identifying constructive and toxic comments separately. Besides, to have an objective assessment for the dataset, we implement a variety of baseline models as traditional Machine Learning and Deep Neural Network-Based models. With the results, we can solve some problems on the online discussions and develop the framework for identifying constructiveness and toxicity Vietnamese social media comments automatically.

A major obstacle to the integration of deep learning models for chest x-ray interpretation into clinical settings is the lack of understanding of their failure modes. In this work, we first investigate whether there are patient subgroups that chest x-ray models are likely to misclassify. We find that patient age and the radiographic finding of lung lesion, pneumothorax or support devices are statistically relevant features for predicting misclassification for some chest x-ray models. Second, we develop misclassification predictors on chest x-ray models using their outputs and clinical features. We find that our best performing misclassification identifier achieves an AUROC close to 0.9 for most diseases. Third, employing our misclassification identifiers, we develop a corrective algorithm to selectively flip model predictions that have high likelihood of misclassification at inference time. We observe F1 improvement on the prediction of Consolidation (0.008 [95\% CI 0.005, 0.010]) and Edema (0.003, [95\% CI 0.001, 0.006]). By carrying out our investigation on ten distinct and high-performing chest x-ray models, we are able to derive insights across model architectures and offer a generalizable framework applicable to other medical imaging tasks.

This article describes research on claim verification carried out using a multiple GAN-based model. The proposed model consists of three pairs of generators and discriminators. The generator and discriminator pairs are responsible for generating synthetic data for supported and refuted claims and claim labels. A theoretical discussion about the proposed model is provided to validate the equilibrium state of the model. The proposed model is applied to the FEVER dataset, and a pre-trained language model is used for the input text data. The synthetically generated data helps to gain information which helps the model to perform better than state of the art models and other standard classifiers.

Learning continuously during all model lifetime is fundamental to deploy machine learning solutions robust to drifts in the data distribution. Advances in Continual Learning (CL) with recurrent neural networks could pave the way to a large number of applications where incoming data is non stationary, like natural language processing and robotics. However, the existing body of work on the topic is still fragmented, with approaches which are application-specific and whose assessment is based on heterogeneous learning protocols and datasets. In this paper, we organize the literature on CL for sequential data processing by providing a categorization of the contributions and a review of the benchmarks. We propose two new benchmarks for CL with sequential data based on existing datasets, whose characteristics resemble real-world applications. We also provide a broad empirical evaluation of CL and Recurrent Neural Networks in class-incremental scenario, by testing their ability to mitigate forgetting with a number of different strategies which are not specific to sequential data processing. Our results highlight the key role played by the sequence length and the importance of a clear specification of the CL scenario.

Adversarial examples are a hot research topic in deep learning nowadays. Subtle, often invisible changes in the data can push our networks to make terrible mistakes. We, as human beings, seem to be way more resilient to these perturbations in our sensory inputs (though not totally immune). There is a certain pattern in our deep learning systems. They achieve remarkable things, but they are also at times delicate and brittle.

There are some tasks that traditional robots -- the rigid and metallic kind -- simply aren't cut out for. Soft-bodied robots, on the other hand, may be able to interact with people more safely or slip into tight spaces with ease. But for robots to reliably complete their programmed duties, they need to know the whereabouts of all their body parts. MIT researchers have developed an algorithm to help engineers design soft robots that collect more useful information about their surroundings. The deep-learning algorithm suggests an optimized placement of sensors within the robot's body, allowing it to better interact with its environment and complete assigned tasks. The advance is a step toward the automation of robot design.

For the last few years, I have been learning and practicing Deep Learning. Participated in several Kaggle competitions and won few medals. During all these years, I tried several cloud platforms and on premise systems. Some of them offered simplicity, flexibility, and affordability. But very few to none offered all of these in one platform.

From Hammurabi's stone tablets to papyrus rolls and leather-bound books, the Arab region has a rich history of recordkeeping and transactional systems that closely matches the evolution of data storage mediums. Even modern-day data management concepts like data provenance and lineage have historic roots in the Arab world; generations of scribes meticulously tracked Islamic prophetic narrations from one narrator to the next, forming lineage chains that originated from central Arabia. Database systems research has been part of the academic culture in the Arab world since the 1970s. High-quality computer science and database education was always available at several universities within the Arab region, such as Alexandria University in Egypt. Many students who went through these programs were drawn to database systems research and became globally prominent, such as Ramez Elmasri (professor at University of Texas, Arlington), Amr El Abbadi (professor at University of California, Santa Barbara), and Walid Aref (professor at Purdue University).

Though Arabic NLP has many challenges, it has seen many successes and developments.

When it was released by Google just a few years ago, a deep-learning model called BERT demonstrated a major step forward in natural language processing (NLP). BERT's core structure, based on a type of neural network known as a Transformer, has become the underpinning for a range of NLP applications, from completing search queries and user-written sentences to language translation. The models even score well on benchmarks intended to test understanding at a high school level, such as Large-scale ReAding Comprehension (RACE) developed at Carnegie Mellon University. In doing so, they have become marketing tools in the artificial intelligence (AI) gold rush. At Nvidia's annual technology conference, president and CEO Jen-Hsun Huang used RACE to claim high performance for his company's implementation of BERT.