We present a memory-augmented approach to condition an autoregressive language model on a knowledge graph. We represent the graph as a collection of relation triples and retrieve relevant relations for a given context to improve text generation. Experiments on WikiText-103, WMT19, and enwik8 English datasets demonstrate that our approach produces a better language model in terms of perplexity and bits per character. We also show that relational memory improves coherence, is complementary to token-based memory, and enables causal interventions. Our model provides a simple yet effective way to combine an autoregressive language model with a knowledge graph for a more coherent and logical generation.

We propose a novel statistical inference paradigm for zero-inflated multiway count data that dispenses with the need to distinguish between true and false zero counts. Our approach ignores all zero entries and applies zero-truncated Poisson regression on the positive counts. Inference is accomplished via tensor completion that imposes low-rank structure on the Poisson parameter space. Our main result shows that an $N$-way rank-$R$ parametric tensor $\boldsymbol{\mathscr{M}}\in(0,\infty)^{I\times \cdots\times I}$ generating Poisson observations can be accurately estimated from approximately $IR^2\log_2^2(I)$ non-zero counts for a nonnegative canonical polyadic decomposition. Several numerical experiments are presented demonstrating that our zero-truncated paradigm is comparable to the ideal scenario where the locations of false zero counts are known a priori.

The benefits of analytics are well-documented. Analytics has helped organisations transform retail experiences, map pathways for trains and trucks, discover extraterrestrial life, and even predict diseases. However, over the past few years, organisations across the globe have wrestled with just how much human error has permeated their analytics attempts, often ending with disastrous results. From crashing spacecraft to sinking ships, transferring billions of dollars to unintended recipients, and causing deaths due to overdose of medication, human error in data analysis has far-reaching ramifications for organisations. The reason for human error in data analysis could be many, such as lack of experience, fatigue or loss of attention, lack of knowledge, or the all-too-common biases in interpreting data. However, what's common among these errors is that they are related to humans reading, processing, analysing, and interpreting data.

Background: Recently, a high number of daily positive COVID-19 cases have been reported in regions with relatively high vaccination rates; hence, booster vaccination has become necessary. In addition, infections caused by the different variants and correlated factors have not been discussed in depth. With large variabilities and different co-factors, it is difficult to use conventional mathematical models to forecast the incidence of COVID-19. Methods: Machine learning based on long short-term memory was applied to forecasting the time series of new daily positive cases (DPC), serious cases, hospitalized cases, and deaths. Data acquired from regions with high rates of vaccination, such as Israel, were blended with the current data of other regions in Japan to factor in the potential effects of vaccination. The protection provided by symptomatic infection was also considered in terms of the population effectiveness of vaccination as well as the waning protection and ratio and infectivity of viral variants. To represent changes in public behavior, public mobility and interactions through social media were also included in the analysis. Findings: Comparing the observed and estimated new DPC in Tel Aviv, Israel, the parameters characterizing vaccination effectiveness and the waning protection from infection were well estimated; the vaccination effectiveness of the second dose after 5 months and the third dose after two weeks from infection by the delta variant were 0.24 and 0.95, respectively. Using the extracted parameters regarding vaccination effectiveness, new cases in three prefectures of Japan were replicated.

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments. Despite their great success, the selection of suitable compression methods and design of details of the compression scheme are difficult, requiring lots of domain knowledge as support, which is not friendly to non-expert users. To make more users easily access to the model compression scheme that best meet their needs, in this paper, we propose AutoMC, an effective automatic tool for model compression. AutoMC builds the domain knowledge on model compression to deeply understand the characteristics and advantages of each compression method under different settings. In addition, it presents a progressive search strategy to efficiently explore pareto optimal compression scheme according to the learned prior knowledge combined with the historical evaluation information. Extensive experimental results show that AutoMC can provide satisfying compression schemes within short time, demonstrating the effectiveness of AutoMC.

In the realm of image processing and computer vision (CV), machine learning (ML) architectures are widely applied. Convolutional neural networks (CNNs) solve a wide range of image processing issues and can solve image compression problem. Compression of images is necessary due to bandwidth and memory constraints. Helpful, redundant, and irrelevant information are three different forms of information found in images. This paper aims to survey recent techniques utilizing mostly lossy image compression using ML architectures including different auto-encoders (AEs) such as convolutional auto-encoders (CAEs), variational auto-encoders (VAEs), and AEs with hyper-prior models, recurrent neural networks (RNNs), CNNs, generative adversarial networks (GANs), principal component analysis (PCA) and fuzzy means clustering. We divide all of the algorithms into several groups based on architecture. We cover still image compression in this survey. Various discoveries for the researchers are emphasized and possible future directions for researchers. The open research problems such as out of memory (OOM), striped region distortion (SRD), aliasing, and compatibility of the frameworks with central processing unit (CPU) and graphics processing unit (GPU) simultaneously are explained. The majority of the publications in the compression domain surveyed are from the previous five years and use a variety of approaches.

Language models (LMs) have introduced a major paradigm shift in Natural Language Processing (NLP) modeling where large pre-trained LMs became integral to most of the NLP tasks. The LMs are intelligent enough to find useful and relevant representations of the language without any supervision. Perhaps, these models are used to fine-tune typical NLP tasks with significantly high accuracy as compared to the traditional approaches. Conversely, the training of these models requires a massively large corpus that is a good representation of the language. English LMs generally perform better than their other language counterparts, due to the availability of massive English corpora. This work elaborates on the design and development of a large Arabic corpus. It consists of over 500 GB of Arabic cleaned text targeted at improving cross-domain knowledge and downstream generalization capability of large-scale language models. Moreover, the corpus is utilized in the training of a large Arabic LM. In order to evaluate the effectiveness of the LM, a number of typical NLP tasks are fine-tuned. The tasks demonstrate a significant boost from 4.5 to 8.5% when compared to tasks fine-tuned on multi-lingual BERT (mBERT). To the best of my knowledge, this is currently the largest clean and diverse Arabic corpus ever collected.

It is widely acknowledged that transparency of automated decision making is crucial for deployability of intelligent systems, and explaining the reasons why some decisions are "good" and some are not is a way to achieving this transparency. We consider two variants of decision making, where "good" decisions amount to alternatives (i) meeting "most" goals, and (ii) meeting "most preferred" goals. We then define, for each variant and notion of "goodness" (corresponding to a number of existing notions in the literature), explanations in two formats, for justifying the selection of an alternative to audiences with differing needs and competences: lean explanations, in terms of goals satisfied and, for some notions of "goodness", alternative decisions, and argumentative explanations, reflecting the decision process leading to the selection, while corresponding to the lean explanations. To define argumentative explanations, we use assumption-based argumentation (ABA), a well-known form of structured argumentation. Specifically, we define ABA frameworks such that "good" decisions are admissible ABA arguments and draw argumentative explanations from dispute trees sanctioning this admissibility. Finally, we instantiate our overall framework for explainable decision-making to accommodate connections between goals and decisions in terms of decision graphs incorporating defeasible and non-defeasible information.

The benefits of analytics are well-documented. Analytics has helped organisations transform retail experiences, map pathways for trains and trucks, discover extraterrestrial life, and even predict diseases. However, over the past few years, organisations across the globe have wrestled with just how much human error has permeated their analytics attempts, often ending with disastrous results. From crashing spacecraft to sinking ships, transferring billions of dollars to unintended recipients, and causing deaths due to overdose of medication, human error in data analysis has far-reaching ramifications for organisations. The reason for human error in data analysis could be many, such as lack of experience, fatigue or loss of attention, lack of knowledge, or the all-too-common biases in interpreting data. However, what's common among these errors is that they are related to humans reading, processing, analysing, and interpreting data.

Testing with quiz questions has proven to be an effective way to assess and improve the educational process. However, manually creating quizzes is tedious and time-consuming. To address this challenge, we present Leaf, a system for generating multiple-choice questions from factual text. In addition to being very well suited for the classroom, Leaf could also be used in an industrial setting, e.g., to facilitate onboarding and knowledge sharing, or as a component of chatbots, question answering systems, or Massive Open Online Courses (MOOCs). The code and the demo are available on GitHub.