Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains. However, most of the existing NER benchmarks lack domain-specialized entity types or do not focus on a certain domain, leading to a less effective cross-domain evaluation. To address these obstacles, we introduce a cross-domain NER dataset (CrossNER), a fully-labeled collection of NER data spanning over five diverse domains with specialized entity categories for different domains. Additionally, we also provide a domain-related corpus since using it to continue pre-training language models (domain-adaptive pre-training) is effective for the domain adaptation. We then conduct comprehensive experiments to explore the effectiveness of leveraging different levels of the domain corpus and pre-training strategies to do domain-adaptive pre-training for the cross-domain task. Results show that focusing on the fractional corpus containing domain-specialized entities and utilizing a more challenging pre-training strategy in domain-adaptive pre-training are beneficial for the NER domain adaptation, and our proposed method can consistently outperform existing cross-domain NER baselines. Nevertheless, experiments also illustrate the challenge of this cross-domain NER task. We hope that our dataset and baselines will catalyze research in the NER domain adaptation area. The code and data are available at https://github.com/zliucr/CrossNER.

The Brazilian economy could benefit from a boost of up to 4.2% within the next decade if companies and governments promote large-scale adoption of artificial intelligence, according to a new study by consulting firm FrontierView commissioned by Microsoft. The potential of GDP increase of more than four percentage points is the most optimistic scenario set out in the reseach, whereby AI use goes beyond automation and is used to create highly skills jobs, drive productivity and economic growth. Even in the most conservative scenario, where the technology is minimally used and only for automation, Brazil could see a 1.8% GDP boost, according to the research. Both scenarios assume that Brazil will adopt all the AI features currently available until 2030. "Our research has found that artificial intelligence can be a driver of Brazil's economic recovery after the Covid-19 pandemic. With the right strategies and investments, the country can increase its economic growth and increase the productivity of the population", said research director for Latin America at FrontierView, Pablo Gonzalez Alonso.

In line with Microsoft's recent announcements in Chile, Brad Smith, President of Microsoft, met with an ESO delegation, headed by its Director General, Xavier Barcons, to sign a new step of their agreement that addresses to optimize and enhance the science made from ESO Paranal Observatory telescopes through Artificial Intelligence (AI). Thanks to this initiative, ESO and Microsoft will work in three areas of great interest for the operations of the Paranal Observatory. The first project is Turbulence Nowcasting, which makes real-time weather and atmospheric predictions to determine whether weather conditions are suitable for different observations. The second project is Anomaly Detection in calibration images taken with ESO s scientific instruments. The visual inspection of the images is replaced by the automatic inspection through Machine Learning algorithms.

Lexical borrowing is very widespread and may affect even those words that play an important role in our daily life. English'mountain', for example, was borrowed from Old French, along with many other words. Researchers from the Pontificia Universidad Católica del Perú and the Max Planck Institute for the Science of Human History have investigated the ability of machine learning algorithms to identify lexical borrowings using word lists from a single language. Results published in the journal PLOS ONE show that current machine-learning methods alone are insufficient for borrowing detection, confirming that additional data and expert knowledge are needed to tackle one of historical linguistics' most pressing challenges. Lexical borrowing, or the direct transfer of words from one language to another, has interested scholars for millennia, as evidenced in Plato's Kratylos dialog, in which Socrates discusses the challenge imposed by borrowed words on etymological studies.

The ability of an agent to comprehend a sentence is tightly connected to the agent's prior experiences and background knowledge. The paper suggests to interpret comprehension as a modality and proposes a complete bimodal logical system that describes an interplay between comprehension and knowledge modalities.

We address the problem of estimating intrinsic distances in a manifold from a finite sample. We prove that the metric space defined by the sample endowed with a computable metric known as sample Fermat distance converges a.s. in the sense of Gromov-Hausdorff. The limiting object is the manifold itself endowed with the population Fermat distance, an intrinsic metric that accounts for both the geometry of the manifold and the density that produces the sample. This result is applied to obtain sample persistence diagrams that converge towards an intrinsic persistence diagram. We show that this method outperforms more standard approaches based on Euclidean norm with theoretical results and computational experiments.

System identification aims to build models of dynamical systems from data. Traditionally, choosing the model requires the designer to balance between two goals of conflicting nature; the model must be rich enough to capture the system dynamics, but not so flexible that it learns spurious random effects from the dataset. It is typically observed that model validation performance follows a U-shaped curve as the model complexity increases. Recent developments in machine learning and statistics, however, have observed situations where a "double-descent" curve subsumes this U-shaped model-performance curve. With a second decrease in performance occurring beyond the point where the model has reached the capacity of interpolating - i.e., (near) perfectly fitting - the training data. To the best of our knowledge, however, such phenomena have not been studied within the context of the identification of dynamic systems. The present paper aims to answer the question: "Can such a phenomenon also be observed when estimating parameters of dynamic systems?" We show the answer is yes, verifying such behavior experimentally both for artificially generated and real-world datasets.

The COVID-19 pandemic has accelerated machine learning (ML) adoption in many areas, resulting in firms increasing their ML investment and implementation efforts. How can emerging markets like Latin America take the opportunity to embrace and adopt artificial intelligence (AI) and ML models more quickly? For more data-driven insights in your Inbox, subscribe to the Refinitiv Perspectives weekly newsletter. The 2020 Refinitiv machine learning survey confirms that ML adoption continues to grow globally, with North America leading adoption rates. Seventy-two percent of firms now say ML is a core component of their business strategy. In many areas, the COVID-19 pandemic has accelerated ML adoption.

Current neural networks-based object detection approaches processing LiDAR point clouds are generally trained from one kind of LiDAR sensors. However, their performances decrease when they are tested with data coming from a different LiDAR sensor than the one used for training, i.e., with a different point cloud resolution. In this paper, R-AGNO-RPN, a region proposal network built on fusion of 3D point clouds and RGB images is proposed for 3D object detection regardless of point cloud resolution. As our approach is designed to be also applied on low point cloud resolutions, the proposed method focuses on object localization instead of estimating refined boxes on reduced data. The resilience to low-resolution point cloud is obtained through image features accurately mapped to Bird's Eye View and a specific data augmentation procedure that improves the contribution of the RGB images. To show the proposed network's ability to deal with different point clouds resolutions, experiments are conducted on both data coming from the KITTI 3D Object Detection and the nuScenes datasets. In addition, to assess its performances, our method is compared to PointPillars, a well-known 3D detection network. Experimental results show that even on point cloud data reduced by $80\%$ of its original points, our method is still able to deliver relevant proposals localization.

Although spatiotemporal graph neural networks have achieved great empirical success in handling multiple correlated time series, they may be impractical in some real-world scenarios due to a lack of sufficient high-quality training data. Furthermore, spatiotemporal graph neural networks lack theoretical interpretation. To address these issues, we put forth a novel mathematically designed framework to analyze spatiotemporal data. Our proposed spatiotemporal graph scattering transform (ST-GST) extends traditional scattering transforms to the spatiotemporal domain. It performs iterative applications of spatiotemporal graph wavelets and nonlinear activation functions, which can be viewed as a forward pass of spatiotemporal graph convolutional networks without training. Since all the filter coefficients in ST-GST are mathematically designed, it is promising for the real-world scenarios with limited training data, and also allows for a theoretical analysis, which shows that the proposed ST-GST is stable to small perturbations of input signals and structures. Finally, our experiments show that i) ST-GST outperforms spatiotemporal graph convolutional networks by an increase of 35% in accuracy for MSR Action3D dataset; ii) it is better and computationally more efficient to design the transform based on separable spatiotemporal graphs than the joint ones; and iii) the nonlinearity in ST-GST is critical to empirical performance. Processing and learning from spatiotemporal data have received increasing attention recently. Examples include: i) skeleton-based human action recognition based on a sequence of human poses (Liu et al. (2019)), which is critical to human behavior understanding (Borges et al. (2013)), and ii) multi-agent trajectory prediction (Hu et al. (2020)), which is critical to robotics and autonomous driving (Shalev-Shwartz et al. (2016)). A common pattern across these applications is that data evolves in both spatial and temporal domains.