Africa
Improving Factual Consistency of Abstractive Summarization via Question Answering
Nan, Feng, Santos, Cicero Nogueira dos, Zhu, Henghui, Ng, Patrick, McKeown, Kathleen, Nallapati, Ramesh, Zhang, Dejiao, Wang, Zhiguo, Arnold, Andrew O., Xiang, Bing
A commonly observed problem with the state-of-the art abstractive summarization models is that the generated summaries can be factually inconsistent with the input documents. The fact that automatic summarization may produce plausible-sounding yet inaccurate summaries is a major concern that limits its wide application. In this paper we present an approach to address factual consistency in summarization. We first propose an efficient automatic evaluation metric to measure factual consistency; next, we propose a novel learning algorithm that maximizes the proposed metric during model training. Through extensive experiments, we confirm that our method is effective in improving factual consistency and even overall quality of the summaries, as judged by both automatic metrics and human evaluation.
PSEUDo: Interactive Pattern Search in Multivariate Time Series with Locality-Sensitive Hashing and Relevance Feedback
Yu, Yuncong, Kruyff, Dylan, Becker, Tim, Behrisch, Michael
We present PSEUDo, an adaptive feature learning technique for exploring visual patterns in multi-track sequential data. Our approach is designed with the primary focus to overcome the uneconomic retraining requirements and inflexible representation learning in current deep learning-based systems. Multi-track time series data are generated on an unprecedented scale due to increased sensors and data storage. These datasets hold valuable patterns, like in neuromarketing, where researchers try to link patterns in multivariate sequential data from physiological sensors to the purchase behavior of products and services. But a lack of ground truth and high variance make automatic pattern detection unreliable. Our advancements are based on a novel query-aware locality-sensitive hashing technique to create a feature-based representation of multivariate time series windows. Most importantly, our algorithm features sub-linear training and inference time. We can even accomplish both the modeling and comparison of 10,000 different 64-track time series, each with 100 time steps (a typical EEG dataset) under 0.8 seconds. This performance gain allows for a rapid relevance feedback-driven adaption of the underlying pattern similarity model and enables the user to modify the speed-vs-accuracy trade-off gradually. We demonstrate superiority of PSEUDo in terms of efficiency, accuracy, and steerability through a quantitative performance comparison and a qualitative visual quality comparison to the state-of-the-art algorithms in the field. Moreover, we showcase the usability of PSEUDo through a case study demonstrating our visual pattern retrieval concepts in a large meteorological dataset. We find that our adaptive models can accurately capture the user's notion of similarity and allow for an understandable exploratory visual pattern retrieval in large multivariate time series datasets.
National Digital Transformation and Smarter Cities: Eight Forces That Will Shape the Future
The world's economy is at a tipping point as digital technologies continue to be embedded into both working and personal lives at an unprecedented rate. By 2023, digitally transformed enterprises will account for more than half of global Gross Domestic Product (GDP). Two overarching factors will drive this trend: the proliferation of digital devices and the rising prominence of the millennial and zoomer (Generation Z) user base. These digital-savvy generations account for 75% of the population in the Middle East today. By 2025, the number of connected devices globally is predicted to reach 100 billion, more than 12 times the number of people in this world.
Israel shared Iranian General Soleimani's cell phones with US intelligence before drone strike: report
Fox News Flash top headlines are here. Check out what's clicking on Foxnews.com. Israel shared three cell phone numbers used by Qasem Soleimani with U.S. intelligence in the hours before American drones unleashed Hellfire missiles on the Iranian general last year, Yahoo News reported Saturday. The revelation sheds new light on the role that Israel played in the killing of Soleimani, who the State Department says was responsible for hundreds of U.S. troop deaths as the head of the Revolutionary Guard's elite Quds Force. The drone strike occurred shortly after midnight on Jan. 2, 2020, as Soleimani and his entourage were leaving Baghdad's international airport.
High-Resolution Poverty Maps in Sub-Saharan Africa
Lee, Kamwoo, Braithwaite, Jeanine
Up-to-date poverty maps are an important tool for policy makers, but until now, have been prohibitively expensive to produce. We propose a generalizable prediction methodology to produce poverty maps at the village level using geospatial data and machine learning algorithms. We tested the proposed method for 25 Sub-Saharan African countries and validated them against survey data. The proposed method can increase the validity of both single country and cross-country estimations leading to higher precision in poverty maps of 44 Sub-Saharan African countries than previously available. More importantly, our cross-country estimation enables the creation of poverty maps when it is not practical or cost-effective to field new national household surveys, as is the case with many low- and middle-income countries.
The effects of regularisation on RNN models for time series forecasting: Covid-19 as an example
Carpenter, Marcus, Luo, Chunbo, Wang, Xiao-Si
Many research papers that propose models to predict the course of the COVID-19 pandemic either use handcrafted statistical models or large neural networks. Even though large neural networks are more powerful than simpler statistical models, they are especially hard to train on small datasets. This paper not only presents a model with grater flexibility than the other proposed neural networks, but also presents a model that is effective on smaller datasets. To improve performance on small data, six regularisation methods were tested. The results show that the GRU combined with 20% Dropout achieved the lowest RMSE scores. The main finding was that models with less access to data relied more on the regulariser. Applying Dropout to a GRU model trained on only 28 days of data reduced the RMSE by 23%.
The Modern Mathematics of Deep Learning
Berner, Julius, Grohs, Philipp, Kutyniok, Gitta, Petersen, Philipp
We describe the new field of mathematical analysis of deep learning. This field emerged around a list of research questions that were not answered within the classical framework of learning theory. These questions concern: the outstanding generalization power of overparametrized neural networks, the role of depth in deep architectures, the apparent absence of the curse of dimensionality, the surprisingly successful optimization performance despite the non-convexity of the problem, understanding what features are learned, why deep architectures perform exceptionally well in physical problems, and which fine aspects of an architecture affect the behavior of a learning task in which way. We present an overview of modern approaches that yield partial answers to these questions. For selected approaches, we describe the main ideas in more detail.
On the Ethical Limits of Natural Language Processing on Legal Text
Tsarapatsanis, Dimitrios, Aletras, Nikolaos
Natural language processing (NLP) methods for analyzing legal text offer legal scholars and practitioners a range of tools allowing to empirically analyze law on a large scale. However, researchers seem to struggle when it comes to identifying ethical limits to using natural language processing (NLP) systems for acquiring genuine insights both about the law and the systems' predictive capacity. In this paper we set out a number of ways in which to think systematically about such issues. We place emphasis on three crucial normative parameters which have, to the best of our knowledge, been underestimated by current debates: (a) the importance of academic freedom, (b) the existence of a wide diversity of legal and ethical norms domestically but even more so internationally and (c) the threat of moralism in research related to computational law. For each of these three parameters we provide specific recommendations for the legal NLP community. Our discussion is structured around the study of a real-life scenario that has prompted recent debate in the legal NLP research community.
Every Resident Evil game, ranked
The perfect Resident Evil game doesn't exist. The series, among the most consequential in gaming, has shifted its focus so often, a "Resident Evil fan" could be many things. One player's definition of a perfect Resident Evil game is another's mark of where the series went astray. Like the Zelda or Mario series, Resident Evil is due some credit for innovating and becoming an industry leader, even if it eventually began to borrow from its action-adventure peers. Still, there are plenty of ideas that persist through each game.