We are happy to announce the first release of 2023 is already here! Finance NLP is a John Snow Lab's product, launched 2022 to provide state-of-the-art, autoscalable, domain-specific NLP on top of Spark. We have updated and improved our more than 20 Financial NLP notebooks, available here. Our Certification training is happening Jan, 2023, where we will be taking a look at all of them and testing some of the features of Finance NLP. Are you willing to join?

WASHINGTON--The Biden administration has begun examining whether checks need to be placed on artificial-intelligence tools such as ChatGPT, amid growing concerns that the technology could be used to discriminate or spread harmful information.

Transformer-based large language models are rapidly advancing in the field of machine learning research, with applications spanning natural language, biology, chemistry, and computer programming. Extreme scaling and reinforcement learning from human feedback have significantly improved the quality of generated text, enabling these models to perform various tasks and reason about their choices. In this paper, we present an Intelligent Agent system that combines multiple large language models for autonomous design, planning, and execution of scientific experiments. We showcase the Agent's scientific research capabilities with three distinct examples, with the most complex being the successful performance of catalyzed cross-coupling reactions. Finally, we discuss the safety implications of such systems and propose measures to prevent their misuse.

We present a scalable machine learning (ML) framework for predicting intensive properties and particularly classifying phases of many-body systems. Scalability and transferability are central to the unprecedented computational efficiency of ML methods. In general, linear-scaling computation can be achieved through the divide and conquer approach, and the locality of physical properties is key to partitioning the system into sub-domains that can be solved separately. Based on the locality assumption, ML model is developed for the prediction of intensive properties of a finite-size block. Predictions of large-scale systems can then be obtained by averaging results of the ML model from randomly sampled blocks of the system. We show that the applicability of this approach depends on whether the block-size of the ML model is greater than the characteristic length scale of the system. In particular, in the case of phase identification across a critical point, the accuracy of the ML prediction is limited by the diverging correlation length. The two-dimensional Ising model is used to demonstrate the proposed framework. We obtain an intriguing scaling relation between the prediction accuracy and the ratio of ML block size over the spin-spin correlation length. Implications for practical applications are also discussed.

Graph neural networks (GNNs) have gained traction in high-energy physics (HEP) for their potential to improve accuracy and scalability. However, their resource-intensive nature and complex operations have motivated the development of symmetry-equivariant architectures. In this work, we introduce EuclidNet, a novel symmetry-equivariant GNN for charged particle tracking. EuclidNet leverages the graph representation of collision events and enforces rotational symmetry with respect to the detector's beamline axis, leading to a more efficient model. We benchmark EuclidNet against the state-of-the-art Interaction Network on the TrackML dataset, which simulates high-pileup conditions expected at the High-Luminosity Large Hadron Collider (HL-LHC). Our results show that EuclidNet achieves near-state-of-the-art performance at small model scales (< 1000 parameters), outperforming the non-equivariant benchmarks. This study paves the way for future investigations into more resource-efficient GNN models for particle tracking in HEP experiments.

Federated learning (FL) provides a variety of privacy advantages by allowing clients to collaboratively train a model without sharing their private data. However, recent studies have shown that private information can still be leaked through shared gradients. To further minimize the risk of privacy leakage, existing defenses usually require clients to locally modify their gradients (e.g., differential privacy) prior to sharing with the server. While these approaches are effective in certain cases, they regard the entire data as a single entity to protect, which usually comes at a large cost in model utility. In this paper, we seek to reconcile utility and privacy in FL by proposing a user-configurable privacy defense, RecUP-FL, that can better focus on the user-specified sensitive attributes while obtaining significant improvements in utility over traditional defenses. Moreover, we observe that existing inference attacks often rely on a machine learning model to extract the private information (e.g., attributes). We thus formulate such a privacy defense as an adversarial learning problem, where RecUP-FL generates slight perturbations that can be added to the gradients before sharing to fool adversary models. To improve the transferability to un-queryable black-box adversary models, inspired by the idea of meta-learning, RecUP-FL forms a model zoo containing a set of substitute models and iteratively alternates between simulations of the white-box and the black-box adversarial attack scenarios to generate perturbations. Extensive experiments on four datasets under various adversarial settings (both attribute inference attack and data reconstruction attack) show that RecUP-FL can meet user-specified privacy constraints over the sensitive attributes while significantly improving the model utility compared with state-of-the-art privacy defenses.

The Serbian language is a Slavic language spoken by over 12 million speakers and well understood by over 15 million people. In the area of natural language processing, it can be considered a low-resourced language. Also, Serbian is considered a high-inflectional language. The combination of many word inflections and low availability of language resources makes natural language processing of Serbian challenging. Nevertheless, over the past three decades, there have been a number of initiatives to develop resources and methods for natural language processing of Serbian, ranging from developing a corpus of free text from books and the internet, annotated corpora for classification and named entity recognition tasks to various methods and models performing these tasks. In this paper, we review the initiatives, resources, methods, and their availability.

Modern computational methods, involving highly sophisticated mathematical formulations, enable several tasks like modeling complex physical phenomenon, predicting key properties and design optimization. The higher fidelity in these computer models makes it computationally intensive to query them hundreds of times for optimization and one usually relies on a simplified model albeit at the cost of losing predictive accuracy and precision. Towards this, data-driven surrogate modeling methods have shown a lot of promise in emulating the behavior of the expensive computer models. However, a major bottleneck in such methods is the inability to deal with high input dimensionality and the need for relatively large datasets. With such problems, the input and output quantity of interest are tensors of high dimensionality. Commonly used surrogate modeling methods for such problems, suffer from requirements like high number of computational evaluations that precludes one from performing other numerical tasks like uncertainty quantification and statistical analysis. In this work, we propose an end-to-end approach that maps a high-dimensional image like input to an output of high dimensionality or its key statistics. Our approach uses two main framework that perform three steps: a) reduce the input and output from a high-dimensional space to a reduced or low-dimensional space, b) model the input-output relationship in the low-dimensional space, and c) enable the incorporation of domain-specific physical constraints as masks. In order to accomplish the task of reducing input dimensionality we leverage principal component analysis, that is coupled with two surrogate modeling methods namely: a) Bayesian hybrid modeling, and b) DeepHyper's deep neural networks. We demonstrate the applicability of the approach on a problem of a linear elastic stress field data.

In situations such as habitat construction, station inspection, or cooperative exploration, incorrect assumptions about the environment or task across the team could lead to mission failure. Thus it is important to resolve any ambiguity about the mission between teammates before embarking on a commanded task. The safeguards guaranteed by formal methods can be used to synthesize correct-by-construction reactive controllers for a robot using Linear Temporal Logic. If a robot fails to synthesize a controller given an instruction, it is clear that there exists a logical inconsistency in the environmental assumptions and/or described interactions. These specifications however are typically crafted in a language unique to the verification framework, requiring the human collaborator to be fluent in the software tool used to construct it. Furthermore, if the controller fails to synthesize, it may prove difficult to easily repair the specification. Language is a natural medium to generate these specifications using modern symbol grounding techniques. Using language empowers non-expert humans to describe tasks to robot teammates while retaining the benefits of formal verification. Additionally, dialogue could be used to inform robots about the environment and/or resolve any ambiguities before mission execution. This paper introduces an architecture for natural language interaction using a symbolic representation that informs the construction of a specification in Linear Temporal Logic. The novel aspect of this approach is that it provides a mechanism for resolving synthesis failure by hypothesizing corrections to the specification that are verified through human-robot dialogue. Experiments involving the proposed architecture are demonstrated using a simulation of an Astrobee robot navigating in the International Space Station.

Attitude is omnipresent in almost every type of text. There has yet to be any relevant research on attitudinal shifts in self-translation. The Chinese version of Between Tears and Laughter is a rare case of self-translation and co-translation in that the first 11 chapters are self-translated by Lin Yutang, and the last 12 chapters by Xu Chengbin. The current study conducted a word frequency analysis of this book's English and Chinese versions with LIWC and AntConc, and made comparative research into Lin Yutang's attitudinal changes. The results show that due to different writing purposes and readerships, there is less anger in Lin's self-translation (M=0.7755, SD=0.3861), which is a significant difference (t=2.2892, This attitudinal change is also reflected in the translations of some n-grams containing anger words. In contrast, there is no significant difference (t=1.88, This paper believes that corpus tools can help co-translators keep their translation consistent in attitude. Introduction Lin Yutang (1895 - 1976), the author of My Country and My People and Moment in Peking, was a world-renowned Chinese writer publishing novels, essays, translations, textbooks, and Chinese-English dictionaries, making outstanding achievements in literature, translation, and language research. He even invented a Chinese typewriter. He wrote more than 30 books in English, most of which describe China's cultural aspects. According to the biography of Lin Yutang written by his daughter Lin Taiyi, Lin was nominated twice for the Nobel Prize for Literature (Lin 1989).