Speech acts are a speakers actions when performing an utterance within a conversation, such as asking, recommending, greeting, or thanking someone, expressing a thought, or making a suggestion. Understanding speech acts helps interpret the intended meaning and actions behind a speakers or writers words. This paper proposes a Twitter dialectal Arabic speech act classification approach based on a transformer deep learning neural network. Twitter and social media, are becoming more and more integrated into daily life. As a result, they have evolved into a vital source of information that represents the views and attitudes of their users. We proposed a BERT based weighted ensemble learning approach to integrate the advantages of various BERT models in dialectal Arabic speech acts classification. We compared the proposed model against several variants of Arabic BERT models and sequence-based models. We developed a dialectal Arabic tweet act dataset by annotating a subset of a large existing Arabic sentiment analysis dataset (ASAD) based on six speech act categories. We also evaluated the models on a previously developed Arabic Tweet Act dataset (ArSAS). To overcome the class imbalance issue commonly observed in speech act problems, a transformer-based data augmentation model was implemented to generate an equal proportion of speech act categories. The results show that the best BERT model is araBERTv2-Twitter models with a macro-averaged F1 score and an accuracy of 0.73 and 0.84, respectively. The performance improved using a BERT-based ensemble method with a 0.74 and 0.85 averaged F1 score and accuracy on our dataset, respectively.

This study presents a new approach for estimating confidence in machine learning model predictions, specifically in regression tasks utilizing Earth Observation (EO) data, with a particular focus on mosquito abundance (MA) estimation. We take advantage of a Variational AutoEncoder architecture, to derive a confidence metric by the latent space representations of EO datasets. This methodology is pivotal in establishing a correlation between the Euclidean distance in latent representations and the Absolute Error (AE) in individual MA predictions. Our research focuses on EO datasets from the Veneto region in Italy and the Upper Rhine Valley in Germany, targeting areas significantly affected by mosquito populations. A key finding is a notable correlation of 0.46 between the AE of MA predictions and the proposed confidence metric. This correlation signifies a robust, new metric for quantifying the reliability and enhancing the trustworthiness of the AI model's predictions in the context of both EO data analysis and mosquito abundance studies.

ECNR advocates MINER, a multiscale approach [31] proposed for implicit neural representation (INR) of image and point cloud Due to its conceptual simplicity and generality, compressive neural data. Similar to MINER, ECNR adaptively decomposes the spatiotemporal representation has emerged as a promising alternative to traditional volume into blocks via the Laplacian pyramid, starting compression methods for managing massive volumetric datasets. As such, a block is only partitioned further The current practice of neural compression utilizes a single large if its residual remains significant, demanding the capture of finer multilayer perceptron (MLP) to encode the global volume, incurring space-time details for accurate signal reconstruction. To fit the local slow training and inference. This paper presents an efficient compressive spatiotemporal blocks at each scale, we utilize multiple small neural representation (ECNR) solution for time-varying data MLPs, permitting fast encoding and decoding, reduced memory compression, utilizing the Laplacian pyramid for adaptive signal consumption, and enhanced reconstruction quality. Following a multiscale structure, we leverage multiple small Different from MINER, ECNR handles 4D (3D+time) volumetric MLPs at each scale for fitting local content or residual blocks. By datasets, while MINER only processes 2D static images or 3D mesh. Working in concert with the multiscale we group similar blocks into clusters, and each cluster consists of structure, we tailor a deep compression strategy to compact the nearly the same number of blocks. We then assign each cluster resulting model. We show the effectiveness of ECNR with multiple to an MLP and effectively train them in parallel. Furthermore, datasets and compare it with state-of-the-art compression methods we leverage a deep compression strategy (including block-guided (mainly SZ3, TTHRESH, and neurcomp).

Recent advances in NLP show that language models retain a discernible level of knowledge in deontological ethics and moral norms. However, existing works often treat morality as binary, ranging from right to wrong. This simplistic view does not capture the nuances of moral judgment. Pluralist moral philosophers argue that human morality can be deconstructed into a finite number of elements, respecting individual differences in moral judgment. In line with this view, we build a pluralist moral sentence embedding space via a state-of-the-art contrastive learning approach. We systematically investigate the embedding space by studying the emergence of relationships among moral elements, both quantitatively and qualitatively. Our results show that a pluralist approach to morality can be captured in an embedding space. However, moral pluralism is challenging to deduce via self-supervision alone and requires a supervised approach with human labels.

The increased application of machine learning (ML) in sensitive domains requires protecting the training data through privacy frameworks, such as differential privacy (DP). DP requires to specify a uniform privacy level $\varepsilon$ that expresses the maximum privacy loss that each data point in the entire dataset is willing to tolerate. Yet, in practice, different data points often have different privacy requirements. Having to set one uniform privacy level is usually too restrictive, often forcing a learner to guarantee the stringent privacy requirement, at a large cost to accuracy. To overcome this limitation, we introduce our novel Personalized-DP Output Perturbation method (PDP-OP) that enables to train Ridge regression models with individual per data point privacy levels. We provide rigorous privacy proofs for our PDP-OP as well as accuracy guarantees for the resulting model. This work is the first to provide such theoretical accuracy guarantees when it comes to personalized DP in machine learning, whereas previous work only provided empirical evaluations. We empirically evaluate PDP-OP on synthetic and real datasets and with diverse privacy distributions. We show that by enabling each data point to specify their own privacy requirement, we can significantly improve the privacy-accuracy trade-offs in DP. We also show that PDP-OP outperforms the personalized privacy techniques of Jorgensen et al. (2015).

These approaches fall into four categories: physicconstrained, Over recent decades, advances in mechanics and electronics serial, parallel, and ensemble strategies. In have led to the development of increasingly sophisticated the physic-constrained category, techniques either integrate systems with complex and multi-physics dynamics, exposing physically meaningful features from first principles into limitations in first principle-based representations [17]. ML models or explicitly include physical constraints, such Modeling these advanced systems purely based on domain as boundary conditions, into the loss function (see, e.g., knowledge may inadequately capture the overall system behavior, the working principle of physics-informed neural networks often necessitating the formulation of complex partial (PINN)) [7,?].

This paper leverages macroscopic models and multi-source spatiotemporal data collected from automatic traffic counters and probe vehicles to accurately estimate traffic flow and travel time in links where these measurements are unavailable. This problem is critical in transportation planning applications where the sensor coverage is low and the planned interventions have network-wide impacts. The proposed model, named the Macroscopic Traffic Estimator (MaTE), can perform network-wide estimations of traffic flow and travel time only using the set of observed measurements of these quantities. Because MaTE is grounded in macroscopic flow theory, all parameters and variables are interpretable. The estimated traffic flow satisfies fundamental flow conservation constraints and exhibits an increasing monotonic relationship with the estimated travel time. Using logit-based stochastic traffic assignment as the principle for routing flow behavior makes the model fully differentiable with respect to the model parameters. This property facilitates the application of computational graphs to learn parameters from vast amounts of spatiotemporal data. We also integrate neural networks and polynomial kernel functions to capture link flow interactions and enrich the mapping of traffic flows into travel times. MaTE also adds a destination choice model and a trip generation model that uses historical data on the number of trips generated by location. Experiments on synthetic data show that the model can accurately estimate travel time and traffic flow in out-of-sample links. Results obtained using real-world multi-source data from a large-scale transportation network suggest that MaTE outperforms data-driven benchmarks, especially in travel time estimation. The estimated parameters of MaTE are also informative about the hourly change in travel demand and supply characteristics of the transportation network.

The labor market is changing rapidly, prompting increased interest in the automatic extraction of occupational skills from text. With the advent of English benchmark job description datasets, there is a need for systems that handle their diversity well. We tackle the complexity in occupational skill datasets tasks -- combining and leveraging multiple datasets for skill extraction, to identify rarely observed skills within a dataset, and overcoming the scarcity of skills across datasets. In particular, we investigate the retrieval-augmentation of language models, employing an external datastore for retrieving similar skills in a dataset-unifying manner. Our proposed method, \textbf{N}earest \textbf{N}eighbor \textbf{O}ccupational \textbf{S}kill \textbf{E}xtraction (NNOSE) effectively leverages multiple datasets by retrieving neighboring skills from other datasets in the datastore. This improves skill extraction \emph{without} additional fine-tuning. Crucially, we observe a performance gain in predicting infrequent patterns, with substantial gains of up to 30\% span-F1 in cross-dataset settings.

Investors and regulators are concerned about financial market volatility and crashes. For this reason, the Volatility index (VIX) was introduced in 1993 by the Chicago Board Options Exchange (CBOE) with the aim of assessing the expected financial market volatility in the short-run, i.e. for the next 30 days, since it is calculated as an implied volatility from the options on the S&P 500 index on this time-to-maturity [1]. The VIX has been proven to be a good predictor of expected stock index shifts, and therefore as an early warning for investor sentiment and financial market turbulences (see e.g., [1], and more recently, [2]). Due to its importance for asset managers and regulators, it would be useful to foresee the values of the index; however, the VIX is very difficult to forecast [3]. There exist several proposals to predict time series found in the literature classified as conventional and modern methods (see e.g., [4] and the references therein).

We introduce new algorithms rooted in scattered data approximation that rely on a random exploration step to ensure that the fill-distance of query points decays at a near-optimal rate. Our algorithms retain the ease of implementation of the classical GP-UCB algorithm and satisfy cumulative regret bounds that nearly match those conjectured in [Vak22], hence solving a COLT open problem. Furthermore, the new algorithms outperform GP-UCB and other popular Bayesian optimization strategies in several examples.